CN108256474A - For identifying the method and apparatus of vegetable - Google Patents
For identifying the method and apparatus of vegetable Download PDFInfo
- Publication number
- CN108256474A CN108256474A CN201810044439.2A CN201810044439A CN108256474A CN 108256474 A CN108256474 A CN 108256474A CN 201810044439 A CN201810044439 A CN 201810044439A CN 108256474 A CN108256474 A CN 108256474A
- Authority
- CN
- China
- Prior art keywords
- vegetable
- probability
- images
- recognized
- recognition result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/68—Food, e.g. fruit or vegetables
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the present application discloses the method and apparatus for identifying vegetable.One specific embodiment of this method includes:Obtain images to be recognized；By the first vegetable identification model of images to be recognized input training in advance, the first recognition result is obtained；The first recognition result based on gained determines to whether there is vegetable in images to be recognized；If there are vegetable, by the second vegetable identification model of images to be recognized input training in advance, the second recognition result is obtained, third recognition result is generated, and export third recognition result based on the second recognition result.The embodiment realizes the identification to vegetable.
Description
Technical field
The invention relates to field of computer technology, and in particular to Internet technical field is more particularly, to known
The method and apparatus of other vegetable.
Background technology
Vegetable refers to the dish of each veriety, such as Steamed Fish Head with Diced Hot Red Peppers, side fish meat etc..With being on the increase for vegetable kind,
People are by being visually typically only capable to identify the vegetables of a small number of kinds.Therefore, user is helped to carry out vegetable to be identified as one kind
Demand.Moreover, vegetable identification is also applied to a variety of different application scenarios, such as the check-out flow of Catering Pubs, intelligence
Service plate is to the voice introduction of vegetable, intelligent refrigerator for monitoring of different vegetables of storage etc..
Invention content
The embodiment of the present application proposes the method and apparatus for identifying vegetable.
In a first aspect, the embodiment of the present application provides a kind of method for identifying vegetable, this method includes：It obtains and waits to know
Other image；By the first vegetable identification model of above-mentioned images to be recognized input training in advance, the first recognition result is obtained, wherein,
Above-mentioned first recognition result include above-mentioned images to be recognized in the probability there are vegetable and the probability there is no vegetable, above-mentioned first
Vegetable identification model is used to characterize the correspondence between image and the first recognition result；The first recognition result based on gained,
It determines to whether there is vegetable in above-mentioned images to be recognized；If there are vegetable, by above-mentioned images to be recognized input training in advance
Second vegetable identification model, obtains the second recognition result, and third recognition result is generated, and export based on above-mentioned second recognition result
Above-mentioned third recognition result, wherein, above-mentioned second recognition result includes the presence of the vegetable classification specified in above-mentioned images to be recognized
The probability of the vegetable under each vegetable classification in set, above-mentioned second vegetable identification model identify for characterizing image and second
As a result the correspondence between.
In some embodiments, above-mentioned second vegetable identification model is by being trained to preset convolutional neural networks
It obtaining, above-mentioned convolutional neural networks include convolutional layer, pond layer, full articulamentum and loss layer, wherein, above-mentioned convolutional layer includes
For extracting with the convolutional layer of the relevant characteristics of image of food materials in vegetable and for extracting and the relevant characteristics of image of vegetable
Convolutional layer, above-mentioned loss layer be used for based on receive with the relevant characteristics of image of food materials in vegetable and with the relevant figure of vegetable
As feature calculation is lost.
In some embodiments, above-mentioned convolutional neural networks train to obtain by following training step：It obtains preset
Sample image set and label information corresponding with each sample image in above-mentioned sample image set, wherein, the sample
Image is the image for showing vegetable, and above-mentioned label information includes being used to indicate the dish that the vegetable that the sample image is shown is belonged to
Other first label of category and the second label for being used to indicate the food materials classification that the food materials that the vegetable includes are belonged to；Utilize machine
Learning method, based on the label letter corresponding to each sample image in above-mentioned sample image set, above-mentioned sample image set
Breath, preset Classification Loss function and back-propagation algorithm are trained above-mentioned convolutional neural networks, obtain the knowledge of the second vegetable
Other model.
In some embodiments, it is above-mentioned that third recognition result is generated based on above-mentioned second recognition result, including：According to numerical value
Size, it is general there are being chosen in the probability of the vegetable under the vegetable classification in above-mentioned vegetable category set from above-mentioned images to be recognized
Rate, and the title of the vegetable classification corresponding to the probability selected and the probability is generated into third recognition result.
In some embodiments, above-mentioned according to numerical values recited, there are above-mentioned vegetable classification collection from above-mentioned images to be recognized
Probability is chosen in the probability of the vegetable under vegetable classification in conjunction, including：According to the sequence that numerical value is descending, wait to know to above-mentioned
Probability in other image there are the vegetable under the vegetable classification in above-mentioned vegetable category set is ranked up, and obtains probability sequence；
Preset number probability is chosen since the stem of above-mentioned probability sequence.
In some embodiments, above-mentioned according to numerical values recited, there are above-mentioned vegetable classification collection from above-mentioned images to be recognized
Probability is chosen in the probability of the vegetable under vegetable classification in conjunction, is further included：There are above-mentioned vegetables from above-mentioned images to be recognized
The probability not less than probability threshold value is chosen in the probability of the vegetable under vegetable classification in category set.
In some embodiments, the above method further includes：It to be used for if there is no vegetables, generation in above-mentioned images to be recognized
It indicates not depositing in above-mentioned fileinfo and above-mentioned images to be recognized there is no the text message of vegetable in above-mentioned images to be recognized
The 4th recognition result is generated, and export above-mentioned 4th recognition result in the probability of vegetable.
In some embodiments, the above method further includes：It is deposited above-mentioned images to be recognized as new sample image
Storage.
Second aspect, the embodiment of the present application provide a kind of device for being used to identify vegetable, which includes：It obtains single
Member is configured to obtain images to be recognized；First recognition unit is configured to above-mentioned images to be recognized input training in advance
First vegetable identification model, obtains the first recognition result, wherein, above-mentioned first recognition result includes depositing in above-mentioned images to be recognized
Probability in vegetable and the probability there is no vegetable, above-mentioned first vegetable identification model are used to characterize image and the first recognition result
Between correspondence；Determination unit is configured to the first recognition result based on gained, determine be in above-mentioned images to be recognized
It is no that there are vegetables；Second recognition unit, if being configured to there are vegetable, by the of above-mentioned images to be recognized input training in advance
Two vegetable identification models, obtain the second recognition result, generate third recognition result based on above-mentioned second recognition result, and export
Third recognition result is stated, wherein, above-mentioned second recognition result includes the presence of the vegetable classification collection specified in above-mentioned images to be recognized
The probability of the vegetable under each vegetable classification in conjunction, above-mentioned second vegetable identification model are tied for characterizing image and the second identification
Correspondence between fruit.
In some embodiments, above-mentioned second vegetable identification model is by being trained to preset convolutional neural networks
It obtaining, above-mentioned convolutional neural networks include convolutional layer, pond layer, full articulamentum and loss layer, wherein, above-mentioned convolutional layer includes
For extracting with the convolutional layer of the relevant characteristics of image of food materials in vegetable and for extracting and the relevant characteristics of image of vegetable
Convolutional layer, above-mentioned loss layer be used for based on receive with the relevant characteristics of image of food materials in vegetable and with the relevant figure of vegetable
As feature calculation is lost.
In some embodiments, above-mentioned convolutional neural networks train to obtain by following training step：It obtains preset
Sample image set and label information corresponding with each sample image in above-mentioned sample image set, wherein, the sample
Image is the image for showing vegetable, and above-mentioned label information includes being used to indicate the dish that the vegetable that the sample image is shown is belonged to
Other first label of category and the second label for being used to indicate the food materials classification that the food materials that the vegetable includes are belonged to；Utilize machine
Learning method, based on the label letter corresponding to each sample image in above-mentioned sample image set, above-mentioned sample image set
Breath, preset Classification Loss function and back-propagation algorithm are trained above-mentioned convolutional neural networks, obtain the knowledge of the second vegetable
Other model.
In some embodiments, above-mentioned second recognition unit includes：Subelement is generated, is configured to according to numerical values recited,
There are choosing probability in the probability of the vegetable under the vegetable classification in above-mentioned vegetable category set from above-mentioned images to be recognized, and
The title of vegetable classification corresponding to the probability selected and the probability is generated into third recognition result.
In some embodiments, above-mentioned generation subelement is further configured to：It is right according to the sequence that numerical value is descending
Probability in above-mentioned images to be recognized there are the vegetable under the vegetable classification in above-mentioned vegetable category set is ranked up, and is obtained general
Rate sequence；Preset number probability is chosen since the stem of above-mentioned probability sequence.
In some embodiments, above-mentioned generation subelement is further configured to：Exist from above-mentioned images to be recognized
The probability not less than probability threshold value is chosen in the probability of the vegetable under vegetable classification in above-mentioned vegetable category set.
In some embodiments, above device further includes：Processing unit, if being configured to not deposit in above-mentioned images to be recognized
In vegetable, then generation is used to indicate the text message that vegetable is not present in above-mentioned images to be recognized, by above-mentioned fileinfo and upper
It states there is no the probability of vegetable the 4th recognition result of generation in images to be recognized, and exports above-mentioned 4th recognition result.
In some embodiments, above device further includes：Storage unit is configured to using above-mentioned images to be recognized as new
Sample image stored.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, which includes：One or more processing
Device；Storage device, for storing one or more programs；When said one or multiple programs are by said one or multiple processors
It performs so that said one or multiple processors are realized such as the method for realization method reflection any in first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, are stored thereon with computer journey
Sequence is realized when above procedure is executed by processor such as the method for realization method reflection any in first aspect.
Method and apparatus provided by the embodiments of the present application for identifying vegetable, by the way that acquired images to be recognized is defeated
Enter the first vegetable identification model of training in advance, to obtain the first recognition result.Then determine to treat based on the first recognition result
It identifies with the presence or absence of vegetable in image, there are during vegetable, images to be recognized to be inputted advance in determining images to be recognized
Trained the second vegetable identification model obtains the second recognition result.It is finally based on the second recognition result generation third identification knot
Fruit, to export third recognition result.So as to be effectively utilized the first vegetable identification model and the second vegetable identification model and
Generation based on the second recognition result to third recognition result realizes the identification to vegetable.
Description of the drawings
By reading the detailed reflection made to non-limiting example made with reference to the following drawings, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is that this application can be applied to exemplary system architecture figures therein；
Fig. 2 is the flow chart for being used to identify one embodiment of the method for vegetable according to the application；
Fig. 3 is the schematic diagram for being used to identify an application scenarios of the method for vegetable according to the application；
Fig. 4 is the structure diagram for being used to identify one embodiment of the device of vegetable according to the application；
Fig. 5 is adapted for the structure diagram of the computer system of the electronic equipment for realizing the embodiment of the present application.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is anti-
The specific embodiment reflected is used only for explaining related invention rather than the restriction to the invention.It also should be noted that in order to
Convenient for reflection, illustrated only in attached drawing and invent relevant part with related.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the method for being used to identify vegetable that can apply the application or the implementation for identifying the device of vegetable
The exemplary system architecture 100 of example.
As shown in Figure 1, system architecture 100 can include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 provide communication link medium.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be interacted with using terminal equipment 101,102,103 by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications can be installed, such as web browser should on terminal device 101,102,103
It is applied with, searching class, image identification class application etc..
Terminal device 101,102,103 can be various electronic equipments, including but not limited to smart mobile phone, tablet computer,
Pocket computer on knee and desktop computer etc..
Server 105 can be to provide the server of various services.For example, server 105 can from terminal device 101,
102nd, 103 images to be recognized is obtained, and to the images to be recognized analyze etc. processing, and by handling result (such as generation
Third recognition result) feed back to terminal device.
It should be noted that generally being held for the method that identifies vegetable by server 105 of being provided of the embodiment of the present application
Row, correspondingly, the device for identifying vegetable is generally positioned in server 105.
It should be pointed out that if images to be recognized is server 105 from locally obtaining, then can in system architecture 100
Not include terminal device 101,102,103.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realization need
Will, can have any number of terminal device, network and server.
With continued reference to Fig. 2, the flow for being used to identify one embodiment of the method for vegetable according to the application is shown
200.This is used for the flow 200 for identifying the method for vegetable, includes the following steps：
Step 201, images to be recognized is obtained.
In the present embodiment, for identifying electronic equipment (such as the service shown in FIG. 1 of the method for vegetable operation thereon
Device 105) images to be recognized can be obtained from the terminal device (such as terminal device shown in FIG. 1 101,102,103) connected.
Above-mentioned electronic equipment can also receive URL (the Uniform Resource of the images to be recognized of terminal device transmission
Locator, uniform resource locator), images to be recognized is obtained according to the URL.Certainly, above-mentioned electronic equipment can also be from local
Obtain images to be recognized.Wherein, which can show the image of vegetable or do not show vegetable
Image.
Step 202, by the first vegetable identification model of images to be recognized input training in advance, the first recognition result is obtained.
In the present embodiment, acquired images to be recognized can be inputted the first dish of training in advance by above-mentioned electronic equipment
Product identification model obtains the first recognition result.Wherein, which can be including there are vegetables in the images to be recognized
Probability and the probability there is no vegetable.The first vegetable identification model can be used for characterizing between image and the first recognition result
Correspondence.It is based on identifying great amount of images and first as an example, the first vegetable identification model can be technical staff
As a result statistics and pre-establish, be stored with multiple images and the mapping table of the correspondence of the first recognition result.
In some optional realization methods of the present embodiment, above-mentioned first vegetable identification model can utilize training sample
The existing convolutional neural networks of this set pair are carried out obtained from Training.The convolutional neural networks can for example include volume
Lamination, pond layer, full articulamentum and loss layer.Wherein, convolutional layer can be used for extracting characteristics of image, and pond layer can be used for pair
The information of input carries out down-sampled (downsample).In addition, the convolutional neural networks can also use various nonlinear activations
Function (such as ReLU (Rectified Linear Units, correct linear unit) function, Sigmoid functions etc.) to information into
Row NONLINEAR CALCULATION.
Step 203, the first recognition result based on gained determines to whether there is vegetable in images to be recognized.
In the present embodiment, above-mentioned electronic equipment can by images to be recognized there are the probability of vegetable and there is no vegetables
Probability be compared, if the probability there is no vegetable is more than probability there are vegetable, above-mentioned electronic equipment can determine to treat
It identifies and vegetable is not present in image.Conversely, above-mentioned electronic equipment can determine that there are vegetables in images to be recognized.
Step 204, in response to determining there are vegetable in images to be recognized, by the second of images to be recognized input training in advance
Vegetable identification model obtains the second recognition result, and third recognition result is generated based on the second recognition result, and exports third identification
As a result.
In the present embodiment, it is determined in images to be recognized there are vegetable in response to above-mentioned electronic equipment, then above-mentioned electronics is set
Standby the second vegetable identification model that images to be recognized can be inputted to training in advance, obtains the second recognition result.Above-mentioned electronics is set
Standby second recognition result that can be based on generates third recognition result, and export third recognition result.For example, if acquired waits to know
The third recognition result can be exported to above-mentioned terminal and set in above-mentioned terminal device, then above-mentioned electronic equipment by other image sources
It is standby.If the images to be recognized is locally obtained from above-mentioned electronic equipment, above-mentioned electronic equipment can be by the third recognition result
It exports to the display screen of above-mentioned electronic equipment or the specified file stored, naturally it is also possible to which output is extremely remote with above-mentioned electronic equipment
The server of journey communication connection.
Wherein, above-mentioned second recognition result can include existing in images to be recognized every in the vegetable category set specified
The probability of vegetable under a vegetable classification.Above-mentioned second vegetable identification model can be used for characterizing image and the second recognition result it
Between correspondence.Here, vegetable classification can be the classification divided according to name of the dish, and vegetable classification can include various names of the dish,
Such as side fish meat, roast duck, Roast duck, roasted goose, Spicy Salted Duck, crispy fried duck, beer duck, potato chicken nugget, Sauted meat shreds with soy bean paste, fried rice with eggs, green pepper
Shredded meat etc..It is based on it should be noted that above-mentioned second vegetable identification model can be technical staff to largely showing vegetable
Image and the second recognition result statistics and pre-establish, be stored with multiple images for showing vegetable and second identification tie
The mapping table of the correspondence of fruit.
In the present embodiment, above-mentioned electronic equipment can be by there are the dishes in above-mentioned vegetable category set in images to be recognized
Category not under vegetable probability in maximum probability corresponding to vegetable classification title generation third recognition result.It assuming that should
The entitled roast duck of vegetable classification corresponding to maximum probability, then the third recognition result can include " roast duck ".
Certainly, above-mentioned electronic equipment can also be by the title of the vegetable classification corresponding to the maximum probability and the maximum probability
Generate third recognition result.Assuming that the maximum probability is 0.99, the entitled roast duck of the vegetable classification corresponding to the maximum probability,
So the third recognition result can include " roast duck -0.99 ".
In some optional realization methods of the present embodiment, above-mentioned electronic equipment can be according to numerical values recited, from waiting to know
In other image there are choosing probability in the probability of the vegetable under the vegetable classification in above-mentioned vegetable category set, and will select
The title generation third recognition result of vegetable classification corresponding to probability and the probability.It should be pointed out that when the third identifies
When as a result including more than two probability, the vegetable item name in the third recognition result can be according to corresponding probability by
It arrives greatly small tactic.
For example, above-mentioned electronic equipment can be according to the descending sequence of numerical value, to there are above-mentioned in the images to be recognized
The probability of the vegetable under vegetable classification in vegetable category set is ranked up, and obtains probability sequence.Above-mentioned electronic equipment can be with
Preset number (such as 3 or 5 etc.) a probability is chosen since the stem of the probability sequence.It should be understood that the preset number is can
With what is be adjusted according to actual needs, the present embodiment does not do any restriction to content in this respect.
For another example above-mentioned electronic equipment can there are the vegetable classes in above-mentioned vegetable category set from the images to be recognized
The probability not less than probability threshold value (such as 0.5 etc.) is chosen in the probability of vegetable under not.It should be understood that the probability threshold value is can
With what is be adjusted according to actual needs, the present embodiment does not do any restriction to content in this respect.
In some optional realization methods of the present embodiment, if above-mentioned electronic equipment determines to be not present in images to be recognized
Vegetable, then above-mentioned electronic equipment, which can generate, is used to indicate in images to be recognized there is no the text message of vegetable, and file is believed
There is no the probability of vegetable in breath and images to be recognized to generate the 4th recognition result, and export the 4th recognition result.For example, this article
This information can include " non-vegetable ".Assuming that the probability be 0.998, the 4th recognition result can include " non-vegetable-
0.998”.4th recognition result can be exported to above-mentioned terminal device, is stored in advance in above-mentioned electronics by above-mentioned electronic equipment
The file of equipment local or the server that is connect with above-mentioned electronic equipment telecommunication etc..
In some optional realization methods of the present embodiment, vegetable identification model can also be by preset convolution
What neural network was trained.Wherein, the multilayer volume which can be indiscipline or training is not completed
Product neural network.The convolutional neural networks can for example include convolutional layer, pond layer, full articulamentum and loss layer.Convolution god
It is extracted through there may be in network with the convolutional layer of the relevant characteristics of image of food materials in vegetable and for extraction and vegetable
The convolutional layer of relevant characteristics of image.The loss layer can be used for special with the relevant image of food materials in vegetable based on receiving
The loss for box counting algorithm synthesis relevant with vegetable of seeking peace.The loss can be used for the process of aiminging drill.
It should be noted that above-mentioned vegetable identification model can be above-mentioned electronic equipment or remotely lead to above-mentioned electronic equipment
What the server of letter connection was trained by performing following training step：
First, preset sample image set and mark corresponding with each sample image in the sample image set are obtained
Sign information.Wherein, which can be the image for showing vegetable, which can include being used to indicate the sample
First label of the vegetable classification that the vegetable that image is shown is belonged to and it is used to indicate the food that the food materials that the vegetable includes are belonged to
Second label of material classification.Wherein, food materials classification can be the classification divided by food materials title, and food materials classification can for example include
Green onion, ginger, garlic, pork, beef, mutton, Chinese cabbage, potato, chicken, duck, snake gourd etc..In addition, sample image set and the sample
The label information corresponding to sample image in this image collection can be stored in advance in the actuating station of the training step (on such as
State electronic equipment or the server being connect with above-mentioned electronic equipment telecommunication) it is local, naturally it is also possible to it is stored in advance in this and holds
In the server that row end is connected, the present embodiment does not do any restriction to content in this respect.
Then, using machine learning method, based on each sample image institute in sample image set, sample image set
Corresponding label information, preset Classification Loss function and back-propagation algorithm are trained preset convolutional neural networks,
Obtain vegetable identification model.Here, in the training process, sample image can be inputted the convolutional Neural net by above-mentioned actuating station
Network, obtaining corresponding with sample image recognition result, (vegetable that the recognition result can include shown by the sample image be
The food materials that the probability and the vegetable of the vegetable under each vegetable classification in above-mentioned vegetable category set are included are the foods specified
The probability of the food materials under each food materials classification in material category set), above-mentioned actuating station can utilize preset Classification Loss letter
For number come the difference that determines second recognition result between label information corresponding to the sample image, above-mentioned electronic equipment can be with
According to the difference, the parameter in the convolutional neural networks is adjusted using preset back-propagation algorithm.
It should be noted that above-mentioned Classification Loss function can be various loss function (such as the Hinge for classification
Loss functions or Softmax Loss functions etc.).In the training process, Classification Loss function can constrain the side of convolution kernel modification
Formula and direction, trained target are to make the value of Classification Loss function minimum.Thus, the ginseng of convolutional neural networks obtained after training
The value of number as Classification Loss function parameter corresponding when being minimum value.
In addition, above-mentioned back-propagation algorithm is alternatively referred to as error backpropagation algorithm or Back Propagation Algorithm.Reversely pass
The learning process for broadcasting algorithm is made of forward-propagating process and back-propagation process.In feedforward network, input signal is through input
Layer input, is calculated by hidden layer, is exported by output layer.By output valve compared with mark value, if there is error, by error reversely by
Output layer in this process, can utilize gradient descent algorithm (such as stochastic gradient descent algorithm) right to input Es-region propagations
Neuron weights (such as parameter of convolution kernel etc. in convolutional layer) are adjusted.
It should be noted that usually there is higher essence by the vegetable identification model that above-mentioned training step is trained
Degree, therefore, it is possible to improve the accuracy of recognition result.
In some optional realization methods of the present embodiment, above-mentioned electronic equipment can be using the images to be recognized as new
Sample image stored.In this way, can continuous enlarged sample image quantity, and the new sample image can be used
In the follow-up training flow of above-mentioned vegetable identification model, above-mentioned vegetable identification model can be made to pass through iteration and more newly arrive raising in advance
Survey accuracy.
With continued reference to Fig. 3, Fig. 3 is the signal for being used to identify the application scenarios of the method for vegetable according to the present embodiment
Figure.In the application scenarios of Fig. 3, first, user can show vegetable by the terminal device held to server upload
Images to be recognized 301；Then, images to be recognized 301 can be inputted the first vegetable identification model of training in advance by server,
The first recognition result is obtained, wherein, which can be including the probability 0.99 there are vegetable in images to be recognized 301
With there is no the probability 0.01 of vegetable.Then, server is by the way that 0.99 and 0.01 are compared, it may be determined that images to be recognized
There are vegetables in 301.Later, images to be recognized 301 can be inputted the second vegetable identification model of training in advance by server, be obtained
To the second recognition result.Then, server can be by preceding 5 probability of the numerical value maximum in the second recognition result and corresponding
The title generation third recognition result 302 of vegetable classification, and third recognition result 302 is exported to terminal device.Wherein, terminal
Images to be recognized 301 and third recognition result 302 can be presented in equipment.
The method that above-described embodiment of the application provides is effectively utilized the first vegetable identification model and the identification of the second vegetable
Model and the generation based on the second recognition result to third recognition result, realize the identification to vegetable.
With further reference to Fig. 4, as the realization to method shown in above-mentioned each figure, this application provides one kind for identifying dish
One embodiment of the device of product, the device embodiment is corresponding with embodiment of the method shown in Fig. 2, which can specifically answer
For in various electronic equipments.
As shown in figure 4, it is used to identify that the device 400 of vegetable to include shown in the present embodiment：Acquiring unit 401, first is known
Other unit 402,403 and second recognition unit 404 of determination unit.Wherein, acquiring unit 401 is configured to obtain figure to be identified
Picture；First recognition unit 402 is configured to, by the first vegetable identification model of above-mentioned images to be recognized input training in advance, obtain
First recognition result, wherein, above-mentioned first recognition result can include that there are the probability and not of vegetable in above-mentioned images to be recognized
There are the probability of vegetable, above-mentioned first vegetable identification model can be used for characterizing the corresponding pass between image and the first recognition result
System；Determination unit 403 is configured to the first recognition result based on gained, determines to whether there is dish in above-mentioned images to be recognized
Product；If the second recognition unit 404 is configured to there are vegetable, by the second vegetable of above-mentioned images to be recognized input training in advance
Identification model obtains the second recognition result, and third recognition result is generated, and export above-mentioned third based on above-mentioned second recognition result
Recognition result, wherein, above-mentioned second recognition result includes in above-mentioned images to be recognized existing in the vegetable category set specified
The probability of vegetable under each vegetable classification, above-mentioned second vegetable identification model are used to characterize between image and the second recognition result
Correspondence.
In the present embodiment, for identifying in the device 400 of vegetable：Acquiring unit 401, determines first recognition unit 402
The specific processing of 403 and second recognition unit 404 of unit and its caused technique effect can be respectively with reference to 2 corresponding embodiments of figure
In step 201, step 202, the related description of step 203 and step 204, details are not described herein.
In some optional realization methods of the present embodiment, above-mentioned second vegetable identification model can be by default
Convolutional neural networks be trained, above-mentioned convolutional neural networks can include convolutional layer, pond layer, full articulamentum and
Loss layer, wherein, above-mentioned convolutional layer can include for extract with vegetable in the relevant characteristics of image of food materials convolutional layer and
For extract with the convolutional layer of the relevant characteristics of image of vegetable, above-mentioned loss layer can be used for based on receive in vegetable
The relevant characteristics of image of food materials and box counting algorithm relevant with vegetable loss.
In some optional realization methods of the present embodiment, above-mentioned convolutional neural networks can be walked by following training
What rapid training obtained：Obtain preset sample image set and corresponding with each sample image in above-mentioned sample image set
Label information, wherein, which can be the image for showing vegetable, and above-mentioned label information can include being used to indicate this
It first label of the vegetable classification that the vegetable that sample image is shown is belonged to and is used to indicate the food materials that the vegetable includes and is belonged to
Food materials classification the second label；Using machine learning method, based in above-mentioned sample image set, above-mentioned sample image set
Each sample image corresponding to label information, preset Classification Loss function and back-propagation algorithm to above-mentioned convolutional Neural
Network is trained, and obtains the second vegetable identification model.
In some optional realization methods of the present embodiment, above-mentioned second recognition unit can include：Generate subelement
(not shown) is configured to according to numerical values recited, and there are in above-mentioned vegetable category set from above-mentioned images to be recognized
Choose probability in the probability of vegetable under vegetable classification, and by the name of the vegetable classification corresponding to the probability selected and the probability
Claim generation third recognition result.
In some optional realization methods of the present embodiment, above-mentioned generation subelement can be further configured to：It presses
According to the sequence that numerical value is descending, to there are the dishes under the vegetable classification in above-mentioned vegetable category set in above-mentioned images to be recognized
The probability of product is ranked up, and obtains probability sequence；Preset number probability is chosen since the stem of above-mentioned probability sequence.
In some optional realization methods of the present embodiment, above-mentioned generation subelement can also be further configured to：
There are choose to be not less than in the probability of the vegetable under the vegetable classification in above-mentioned vegetable category set from above-mentioned images to be recognized
The probability of probability threshold value.
In some optional realization methods of the present embodiment, above device 400 can also include：Processing unit is (in figure
It is not shown), if being configured in above-mentioned images to be recognized there is no vegetable, generation is used to indicate in above-mentioned images to be recognized not
There are the text messages of vegetable, and the probability generation the 4th that vegetable is not present in above-mentioned fileinfo and above-mentioned images to be recognized is known
Not as a result, and exporting above-mentioned 4th recognition result.
In some optional realization methods of the present embodiment, above device 400 can also include：Storage unit is (in figure
It is not shown), it is configured to store above-mentioned images to be recognized as new sample image.
The device that above-described embodiment of the application provides is effectively utilized the first vegetable identification model and the identification of the second vegetable
Model and the generation based on the second recognition result to third recognition result, realize the identification to vegetable.
Below with reference to Fig. 5, it illustrates suitable for being used for realizing the computer system 500 of the electronic equipment of the embodiment of the present application
Structure diagram.Electronic equipment shown in Fig. 5 is only an example, to the function of the embodiment of the present application and should not use model
Shroud carrys out any restrictions.
As shown in figure 5, computer system 500 includes central processing unit (CPU) 501, it can be read-only according to being stored in
Program in memory (ROM) 502 or be loaded into program in random access storage device (RAM) 503 from storage section 508 and
Perform various appropriate actions and processing.In RAM 503, also it is stored with system 500 and operates required various programs and data.
CPU 501, ROM 502 and RAM 503 are connected with each other by bus 504.Input/output (I/O) interface 505 is also connected to always
Line 504.
I/O interfaces 505 are connected to lower component：Importation 506 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 507 of spool (CRT), liquid crystal display (LCD) etc. and loud speaker etc.；Storage section 508 including hard disk etc.；
And the communications portion 509 of the network interface card including LAN card, modem etc..Communications portion 509 via such as because
The network of spy's net performs communication process.Driver 510 is also according to needing to be connected to I/O interfaces 505.Detachable media 511, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on driver 510, as needed in order to be read from thereon
Computer program be mounted into storage section 508 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart reflection
Software program.For example, embodiment of the disclosure includes a kind of computer program product, including being carried on computer-readable medium
On computer program, which includes for the program code of the method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 509 and/or from detachable media
511 are mounted.When the computer program is performed by central processing unit (CPU) 501, perform what is limited in the system of the application
Above-mentioned function.
It should be noted that the computer-readable medium shown in the application can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two arbitrarily combines.Computer readable storage medium for example can be --- but not
It is limited to --- electricity, magnetic, optical, electromagnetic, system, device or the device of infrared ray or semiconductor or arbitrary above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to：Electrical connection with one or more conducting wires, just
It takes formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type and may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In this application, computer readable storage medium can any include or store journey
The tangible medium of sequence, the program can be commanded the either device use or in connection of execution system, device.And at this
In application, computer-readable signal media can include in a base band or as a carrier wave part propagation data-signal,
Wherein carry computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including but it is unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By instruction execution system, device either device use or program in connection.It is included on computer-readable medium
Program code can be transmitted with any appropriate medium, including but not limited to：Wirelessly, electric wire, optical cable, RF etc. or above-mentioned
Any appropriate combination.
Flow chart and block diagram in attached drawing, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
Architectural framework in the cards, function and the operation of sequence product.In this regard, each box in flow chart or block diagram can generation
The part of one module of table, program segment or code, a part for above-mentioned module, program segment or code include one or more
The executable instruction of logic function as defined in being used to implement.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also be occurred with being different from the sequence marked in attached drawing.For example, two boxes succeedingly represented are practical
On can perform substantially in parallel, they can also be performed in the opposite order sometimes, this is depended on the functions involved.Also
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and perform rule
The group of specialized hardware and computer instruction is realized or can be used to the dedicated hardware based system of fixed functions or operations
It closes to realize.
Being reflected in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.The unit reflected can also be set in the processor, for example, can be reflected as：A kind of processor packet
Include acquiring unit, the first recognition unit, determination unit and the second recognition unit.Wherein, the title of these units is in certain situation
Under do not form restriction to the unit in itself, for example, acquiring unit can also be reflected as " obtaining the list of images to be recognized
Member ".
As on the other hand, present invention also provides a kind of computer-readable medium, which can be
Included in the electronic equipment reflected in above-described embodiment；Can also be individualism, and without be incorporated the electronic equipment in.
Above computer readable medium carries one or more program, and when said one or multiple programs, by one, the electronics is set
During standby execution so that the electronic equipment includes：Obtain images to be recognized；By the first of above-mentioned images to be recognized input training in advance
Vegetable identification model obtains the first recognition result, wherein, above-mentioned first recognition result is including there are dishes in above-mentioned images to be recognized
The probability of product and the probability there is no vegetable, above-mentioned first vegetable identification model are used to characterize between image and the first recognition result
Correspondence；The first recognition result based on gained determines to whether there is vegetable in above-mentioned images to be recognized；If there are dishes
Product then by the second vegetable identification model of above-mentioned images to be recognized input training in advance, obtain the second recognition result, based on above-mentioned
Second recognition result generates third recognition result, and exports above-mentioned third recognition result, wherein, above-mentioned second recognition result includes
There is the probability of the vegetable under each vegetable classification in the vegetable category set specified in above-mentioned images to be recognized, above-mentioned second
Vegetable identification model is used to characterize the correspondence between image and the second recognition result.
The preferred embodiment and the explanation to institute's application technology principle that above reflection is only the application.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to the technology that the specific combination of above-mentioned technical characteristic forms
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
The other technical solutions for arbitrarily combining and being formed.Such as features described above has similar work(with (but not limited to) disclosed herein
The technical solution that the technical characteristic of energy is replaced mutually and formed.
Claims (18)
1. a kind of method for identifying vegetable, including：
Obtain images to be recognized；
By the first vegetable identification model of images to be recognized input training in advance, the first recognition result is obtained, wherein, it is described
First recognition result includes the probability there are vegetable and the probability there is no vegetable in the images to be recognized, first vegetable
Identification model is used to characterize the correspondence between image and the first recognition result；
The first recognition result based on gained determines to whether there is vegetable in the images to be recognized；
If there are vegetable, by the second vegetable identification model of images to be recognized input training in advance, the second identification is obtained
As a result, generating third recognition result based on second recognition result, and the third recognition result is exported, wherein, described the
Two recognition results include the vegetable for having under each vegetable classification in the vegetable category set specified in the images to be recognized
Probability, the second vegetable identification model is used to characterize correspondence between image and the second recognition result.
2. according to the method described in claim 1, wherein, the second vegetable identification model is by preset convolutional Neural
What network was trained, the convolutional neural networks include convolutional layer, pond layer, full articulamentum and loss layer, wherein, institute
Convolutional layer is stated including the convolutional layer for extraction and the relevant characteristics of image of the food materials in vegetable and related with vegetable for extracting
Characteristics of image convolutional layer, the loss layer be used for based on receive with the relevant characteristics of image of food materials in vegetable and with
The relevant box counting algorithm loss of vegetable.
3. according to the method described in claim 2, wherein, the convolutional neural networks are to train to obtain by following training step
's：
Preset sample image set and label information corresponding with each sample image in the sample image set are obtained,
Wherein, which is the image for showing vegetable, and the label information includes being used to indicate the dish that the sample image is shown
First label of the vegetable classification that product are belonged to and it is used to indicate the food materials that the vegetable includes are belonged to the second of food materials classification
Label；
Using machine learning method, based on each sample image institute in the sample image set, the sample image set
Corresponding label information, preset Classification Loss function and back-propagation algorithm are trained the convolutional neural networks, obtain
To the second vegetable identification model.
4. it is described that third recognition result is generated based on second recognition result according to the method described in claim 1, wherein,
Including：
According to numerical values recited, there are the vegetables under the vegetable classification in the vegetable category set from the images to be recognized
Probability is chosen in probability, and the title generation third identification of the vegetable classification corresponding to the probability selected and the probability is tied
Fruit.
5. according to the method described in claim 4, wherein, described according to numerical values recited, there are institutes from the images to be recognized
It states in the probability of the vegetable under the vegetable classification in vegetable category set and chooses probability, including：
According to the sequence that numerical value is descending, to there are the vegetable classifications in the vegetable category set in the images to be recognized
Under the probability of vegetable be ranked up, obtain probability sequence；
Preset number probability is chosen since the stem of the probability sequence.
6. according to the method described in claim 4, wherein, described according to numerical values recited, there are institutes from the images to be recognized
It states in the probability of the vegetable under the vegetable classification in vegetable category set and chooses probability, further include：
There are chosen not in the probability of the vegetable under the vegetable classification in the vegetable category set from the images to be recognized
Less than the probability of probability threshold value.
7. according to the method described in claim 1, wherein, the method further includes：
If there is no vegetable in the images to be recognized, generation is used to indicate the text that vegetable is not present in the images to be recognized
The probability that vegetable is not present in the fileinfo and the images to be recognized is generated the 4th recognition result, and defeated by this information
Go out the 4th recognition result.
8. according to the method described in claim 1, wherein, the method further includes：
It is stored the images to be recognized as new sample image.
9. it is a kind of for identifying the device of vegetable, including：
Acquiring unit is configured to obtain images to be recognized；
First recognition unit is configured to, by the first vegetable identification model of images to be recognized input training in advance, obtain
First recognition result, wherein, first recognition result include the images to be recognized in there are vegetable probability and be not present
The probability of vegetable, the first vegetable identification model are used to characterize the correspondence between image and the first recognition result；
Determination unit is configured to the first recognition result based on gained, determines to whether there is vegetable in the images to be recognized；
Second recognition unit, if being configured to there are vegetable, by the second vegetable of images to be recognized input training in advance
Identification model obtains the second recognition result, and third recognition result is generated, and export the third based on second recognition result
Recognition result, wherein, second recognition result includes in the images to be recognized existing in the vegetable category set specified
The probability of vegetable under each vegetable classification, the second vegetable identification model are used to characterize between image and the second recognition result
Correspondence.
10. device according to claim 9, wherein, the second vegetable identification model is by preset convolution god
It being trained through network, the convolutional neural networks include convolutional layer, pond layer, full articulamentum and loss layer, wherein,
The convolutional layer includes extracting with the convolutional layer of the relevant characteristics of image of food materials in vegetable and for extracting and vegetable phase
The convolutional layer of the characteristics of image of pass, the loss layer be used for based on receive with the relevant characteristics of image of food materials in vegetable and
Box counting algorithm loss relevant with vegetable.
11. device according to claim 10, wherein, the convolutional neural networks are trained by following training step
It arrives：
Preset sample image set and label information corresponding with each sample image in the sample image set are obtained,
Wherein, which is the image for showing vegetable, and the label information includes being used to indicate the dish that the sample image is shown
First label of the vegetable classification that product are belonged to and it is used to indicate the food materials that the vegetable includes are belonged to the second of food materials classification
Label；
Using machine learning method, based on each sample image institute in the sample image set, the sample image set
Corresponding label information, preset Classification Loss function and back-propagation algorithm are trained the convolutional neural networks, obtain
To the second vegetable identification model.
12. device according to claim 9, wherein, second recognition unit includes：
Subelement is generated, is configured to according to numerical values recited, there are in the vegetable category set from the images to be recognized
Vegetable classification under vegetable probability in choose probability, and by the vegetable classification corresponding to the probability selected and the probability
Title generates third recognition result.
13. device according to claim 12, wherein, the generation subelement is further configured to：
According to the sequence that numerical value is descending, to there are the vegetable classifications in the vegetable category set in the images to be recognized
Under the probability of vegetable be ranked up, obtain probability sequence；
Preset number probability is chosen since the stem of the probability sequence.
14. device according to claim 12, wherein, the generation subelement is further configured to：
There are chosen not in the probability of the vegetable under the vegetable classification in the vegetable category set from the images to be recognized
Less than the probability of probability threshold value.
15. device according to claim 9, wherein, described device further includes：
Processing unit, if being configured in the images to be recognized there is no vegetable, generation is used to indicate the figure to be identified
The text message of vegetable is not present as in, the probability that vegetable is not present in the fileinfo and the images to be recognized is generated
4th recognition result, and export the 4th recognition result.
16. device according to claim 9, wherein, described device further includes：
Storage unit is configured to store the images to be recognized as new sample image.
17. a kind of electronic equipment, including：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processors are real
Now such as method according to any one of claims 1-8.
18. a kind of computer readable storage medium, is stored thereon with computer program, wherein, described program is executed by processor
Shi Shixian methods for example according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810044439.2A CN108256474A (en) | 2018-01-17 | 2018-01-17 | For identifying the method and apparatus of vegetable |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810044439.2A CN108256474A (en) | 2018-01-17 | 2018-01-17 | For identifying the method and apparatus of vegetable |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108256474A true CN108256474A (en) | 2018-07-06 |
Family
ID=62726590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810044439.2A Pending CN108256474A (en) | 2018-01-17 | 2018-01-17 | For identifying the method and apparatus of vegetable |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108256474A (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165656A (en) * | 2018-07-24 | 2019-01-08 | 上海常仁信息科技有限公司 | A kind of feature information extraction system and method for vegetable image |
| CN109214272A (en) * | 2018-07-17 | 2019-01-15 | 北京陌上花科技有限公司 | A kind of image-recognizing method and device |
| CN109299648A (en) * | 2018-07-24 | 2019-02-01 | 上海常仁信息科技有限公司 | A kind of identification device for capableing of vegetable identification |
| CN109299782A (en) * | 2018-08-02 | 2019-02-01 | 北京奇安信科技有限公司 | A kind of data processing method and device based on deep learning model |
| CN109902733A (en) * | 2019-02-22 | 2019-06-18 | 北京三快在线科技有限公司 | The method, apparatus and storage medium of typing Item Information |
| CN110059551A (en) * | 2019-03-12 | 2019-07-26 | 五邑大学 | A kind of automatic checkout system of food based on image recognition |
| CN110110577A (en) * | 2019-01-22 | 2019-08-09 | 口碑(上海)信息技术有限公司 | Identify method and device, the storage medium, electronic device of name of the dish |
| CN110276405A (en) * | 2019-06-26 | 2019-09-24 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
| CN110580297A (en) * | 2019-08-02 | 2019-12-17 | 北京三快在线科技有限公司 | Merchant and dish matching method and device based on dish image and electronic equipment |
| CN110895781A (en) * | 2019-10-29 | 2020-03-20 | 北京三快在线科技有限公司 | Dish type recommendation method and device, electronic equipment and storage medium |
| CN110969047A (en) * | 2018-09-28 | 2020-04-07 | 珠海格力电器股份有限公司 | Method and device for identifying food materials and refrigerator |
| CN111046849A (en) * | 2019-12-30 | 2020-04-21 | 珠海格力电器股份有限公司 | Kitchen safety implementation method and device, intelligent terminal and storage medium |
| CN111143585A (en) * | 2019-04-11 | 2020-05-12 | 王晓东 | Automatic big data sorting method |
| CN111274972A (en) * | 2020-01-21 | 2020-06-12 | 北京妙医佳健康科技集团有限公司 | Dish identification method and device based on metric learning |
| CN111310520A (en) * | 2018-12-11 | 2020-06-19 | 阿里巴巴集团控股有限公司 | Dish identification method, cash registering method, dish order prompting method and related device |
| CN111325067A (en) * | 2018-12-14 | 2020-06-23 | 北京金山云网络技术有限公司 | Illegal video identification method and device and electronic equipment |
| CN111444345A (en) * | 2020-03-30 | 2020-07-24 | 拉扎斯网络科技（上海）有限公司 | Dish name classification method and device |
| CN111563518A (en) * | 2020-03-20 | 2020-08-21 | 时时同云科技(成都)有限责任公司 | Dish image identification method and device based on edge calculation |
| CN111597862A (en) * | 2019-02-21 | 2020-08-28 | 杭州海康威视数字技术股份有限公司 | Dish category identification method and device and electronic equipment |
| CN111783574A (en) * | 2020-06-17 | 2020-10-16 | 李利明 | Meal image recognition method and device and storage medium |
| CN111832590A (en) * | 2019-04-23 | 2020-10-27 | 北京京东尚科信息技术有限公司 | Article identification method and system |
| CN112308175A (en) * | 2020-02-26 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Method and device for identifying an item |
| CN112990628A (en) * | 2019-12-16 | 2021-06-18 | 顺丰科技有限公司 | Sorting equipment scheduling method and device and computer readable storage medium |
| CN113191308A (en) * | 2021-05-18 | 2021-07-30 | 深圳市创智链科技有限公司 | Method and equipment for cascade classification recognition |
| CN113486913A (en) * | 2020-09-30 | 2021-10-08 | 青岛海信电子产业控股股份有限公司 | Food material identification method and equipment |
| CN113807146A (en) * | 2020-06-15 | 2021-12-17 | 深圳绿米联创科技有限公司 | Door lock identification method and device and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529564A (en) * | 2016-09-26 | 2017-03-22 | 浙江工业大学 | Food image automatic classification method based on convolutional neural networks |
| US20170148431A1 (en) * | 2015-11-25 | 2017-05-25 | Baidu Usa Llc | End-to-end speech recognition |
| CN106845527A (en) * | 2016-12-29 | 2017-06-13 | 南京江南博睿高新技术研究院有限公司 | A kind of vegetable recognition methods |
| CN106874913A (en) * | 2016-12-29 | 2017-06-20 | 南京江南博睿高新技术研究院有限公司 | A kind of vegetable detection method |
-
2018
- 2018-01-17 CN CN201810044439.2A patent/CN108256474A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170148431A1 (en) * | 2015-11-25 | 2017-05-25 | Baidu Usa Llc | End-to-end speech recognition |
| CN106529564A (en) * | 2016-09-26 | 2017-03-22 | 浙江工业大学 | Food image automatic classification method based on convolutional neural networks |
| CN106845527A (en) * | 2016-12-29 | 2017-06-13 | 南京江南博睿高新技术研究院有限公司 | A kind of vegetable recognition methods |
| CN106874913A (en) * | 2016-12-29 | 2017-06-20 | 南京江南博睿高新技术研究院有限公司 | A kind of vegetable detection method |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109214272A (en) * | 2018-07-17 | 2019-01-15 | 北京陌上花科技有限公司 | A kind of image-recognizing method and device |
| CN109214272B (en) * | 2018-07-17 | 2024-07-05 | 北京陌上花科技有限公司 | Image recognition method and device |
| CN109299648A (en) * | 2018-07-24 | 2019-02-01 | 上海常仁信息科技有限公司 | A kind of identification device for capableing of vegetable identification |
| CN109165656A (en) * | 2018-07-24 | 2019-01-08 | 上海常仁信息科技有限公司 | A kind of feature information extraction system and method for vegetable image |
| CN109299782A (en) * | 2018-08-02 | 2019-02-01 | 北京奇安信科技有限公司 | A kind of data processing method and device based on deep learning model |
| CN110969047A (en) * | 2018-09-28 | 2020-04-07 | 珠海格力电器股份有限公司 | Method and device for identifying food materials and refrigerator |
| CN111310520B (en) * | 2018-12-11 | 2023-11-21 | 阿里巴巴集团控股有限公司 | Dish identification method, cashing method, dish ordering method and related devices |
| CN111310520A (en) * | 2018-12-11 | 2020-06-19 | 阿里巴巴集团控股有限公司 | Dish identification method, cash registering method, dish order prompting method and related device |
| CN111325067A (en) * | 2018-12-14 | 2020-06-23 | 北京金山云网络技术有限公司 | Illegal video identification method and device and electronic equipment |
| CN110110577A (en) * | 2019-01-22 | 2019-08-09 | 口碑(上海)信息技术有限公司 | Identify method and device, the storage medium, electronic device of name of the dish |
| CN110110577B (en) * | 2019-01-22 | 2020-11-10 | 口碑(上海)信息技术有限公司 | Method and device for identifying dish name, storage medium and electronic device |
| CN111597862A (en) * | 2019-02-21 | 2020-08-28 | 杭州海康威视数字技术股份有限公司 | Dish category identification method and device and electronic equipment |
| CN109902733A (en) * | 2019-02-22 | 2019-06-18 | 北京三快在线科技有限公司 | The method, apparatus and storage medium of typing Item Information |
| CN110059551A (en) * | 2019-03-12 | 2019-07-26 | 五邑大学 | A kind of automatic checkout system of food based on image recognition |
| CN111143585A (en) * | 2019-04-11 | 2020-05-12 | 王晓东 | Automatic big data sorting method |
| CN111832590B (en) * | 2019-04-23 | 2024-03-05 | 北京京东尚科信息技术有限公司 | Article identification method and system |
| CN111832590A (en) * | 2019-04-23 | 2020-10-27 | 北京京东尚科信息技术有限公司 | Article identification method and system |
| WO2020215952A1 (en) * | 2019-04-23 | 2020-10-29 | 北京京东尚科信息技术有限公司 | Object recognition method and system |
| CN110276405A (en) * | 2019-06-26 | 2019-09-24 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
| CN110276405B (en) * | 2019-06-26 | 2022-03-01 | 北京百度网讯科技有限公司 | Method and apparatus for outputting information |
| CN110580297A (en) * | 2019-08-02 | 2019-12-17 | 北京三快在线科技有限公司 | Merchant and dish matching method and device based on dish image and electronic equipment |
| CN110895781A (en) * | 2019-10-29 | 2020-03-20 | 北京三快在线科技有限公司 | Dish type recommendation method and device, electronic equipment and storage medium |
| CN112990628A (en) * | 2019-12-16 | 2021-06-18 | 顺丰科技有限公司 | Sorting equipment scheduling method and device and computer readable storage medium |
| CN111046849A (en) * | 2019-12-30 | 2020-04-21 | 珠海格力电器股份有限公司 | Kitchen safety implementation method and device, intelligent terminal and storage medium |
| CN111274972B (en) * | 2020-01-21 | 2023-08-29 | 北京妙医佳健康科技集团有限公司 | Dish identification method and device based on measurement learning |
| CN111274972A (en) * | 2020-01-21 | 2020-06-12 | 北京妙医佳健康科技集团有限公司 | Dish identification method and device based on metric learning |
| CN112308175A (en) * | 2020-02-26 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Method and device for identifying an item |
| CN111563518A (en) * | 2020-03-20 | 2020-08-21 | 时时同云科技(成都)有限责任公司 | Dish image identification method and device based on edge calculation |
| CN111563518B (en) * | 2020-03-20 | 2023-08-11 | 时时同云科技(成都)有限责任公司 | Dish image recognition method and device based on edge calculation |
| CN111444345A (en) * | 2020-03-30 | 2020-07-24 | 拉扎斯网络科技（上海）有限公司 | Dish name classification method and device |
| CN113807146A (en) * | 2020-06-15 | 2021-12-17 | 深圳绿米联创科技有限公司 | Door lock identification method and device and electronic equipment |
| CN111783574A (en) * | 2020-06-17 | 2020-10-16 | 李利明 | Meal image recognition method and device and storage medium |
| CN111783574B (en) * | 2020-06-17 | 2024-02-23 | 李利明 | Meal image recognition method, device and storage medium |
| CN113486913A (en) * | 2020-09-30 | 2021-10-08 | 青岛海信电子产业控股股份有限公司 | Food material identification method and equipment |
| CN113191308A (en) * | 2021-05-18 | 2021-07-30 | 深圳市创智链科技有限公司 | Method and equipment for cascade classification recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108256474A (en) | For identifying the method and apparatus of vegetable | |
| CN108256476A (en) | For identifying the method and apparatus of fruits and vegetables | |
| CN108038469A (en) | Method and apparatus for detecting human body | |
| CN107168952A (en) | Information generating method and device based on artificial intelligence | |
| CN108229485A (en) | For testing the method and apparatus of user interface | |
| CN108427708A (en) | Data processing method, device, storage medium and electronic device | |
| CN108171191B (en) | Method and apparatus for detecting face | |
| CN109446990A (en) | Method and apparatus for generating information | |
| CN107526725A (en) | The method and apparatus for generating text based on artificial intelligence | |
| CN109712711A (en) | Health evaluating method, apparatus, electronic equipment and medium based on machine learning | |
| CN109101919A (en) | Method and apparatus for generating information | |
| CN109360028A (en) | Method and apparatus for pushed information | |
| CN109583297A (en) | Retina OCT volume data identification method and device | |
| CN109308490A (en) | Method and apparatus for generating information | |
| CN108171275A (en) | For identifying the method and apparatus of flowers | |
| Morol et al. | Food recipe recommendation based on ingredients detection using deep learning | |
| CN108960110A (en) | Method and apparatus for generating information | |
| CN108256591A (en) | For the method and apparatus of output information | |
| CN107578034A (en) | information generating method and device | |
| CN108734296A (en) | Optimize method, apparatus, electronic equipment and the medium of the training data of supervised learning | |
| CN108388563A (en) | Information output method and device | |
| CN109101309A (en) | For updating user interface method and device | |
| CN116888617A (en) | Recipe providing device and method | |
| CN108805867A (en) | Method and apparatus for exporting tobacco leaf degree information | |
| CN109165570A (en) | Method and apparatus for generating information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180706 |