CN109064464A - Method and apparatus for detecting battery pole piece burr - Google Patents
Method and apparatus for detecting battery pole piece burr Download PDFInfo
- Publication number
- CN109064464A CN109064464A CN201810906761.1A CN201810906761A CN109064464A CN 109064464 A CN109064464 A CN 109064464A CN 201810906761 A CN201810906761 A CN 201810906761A CN 109064464 A CN109064464 A CN 109064464A
- Authority
- CN
- China
- Prior art keywords
- burr
- battery pole
- pole piece
- image
- sample
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Chemical & Material Sciences (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the present application discloses the method and apparatus for detecting battery pole piece burr.One specific embodiment of this method includes: to obtain for image captured by battery pole piece as image to be detected；In response to determining that image to be detected includes battery pole piece burr areas, the position of the classification and battery pole piece burr areas of burr indicated by battery pole piece burr areas in image to be detected is determined.The embodiment is realized through the battery pole piece burr areas in image to be detected, determines the classification of battery pole piece burr.
Description
Technical field
The invention relates to field of computer technology, and in particular to for detecting the method and dress of battery pole piece burr
It sets.
Background technique
In battery industry, the quality of battery pole piece and the quality of battery are closely related.Therefore, battery pole piece production process
In, it is often necessary to the surface of battery pole piece is detected, checks whether that there are burrs.Currently, the inspection to battery pole piece surface
It surveys, is mainly realized by following two mode.First, the surface of battery pole piece is shot, then, passes through technical staff
The picture taken is analyzed, and then determines that the surface of battery pole piece whether there is burr.Second, memory technology personnel are first
Then preceding testing result according to the testing result that these are stored, is analyzed the image taken, and then determine battery
The surface of pole piece whether there is burr.
Summary of the invention
The embodiment of the present application proposes the method and apparatus for detecting battery pole piece burr.
In a first aspect, the embodiment of the present application provides a kind of method for detecting battery pole piece burr, this method comprises:
It obtains for image captured by battery pole piece as image to be detected；In response to determining that image to be detected includes battery pole piece hair
Spine area domain, the classification for determining burr indicated by battery pole piece burr areas and battery pole piece burr areas are in image to be detected
Position.
In some embodiments, classification and the battery pole piece burr area of burr indicated by battery pole piece burr areas are determined
Position of the domain in described image to be detected, comprising: image to be detected is input to burr detection model trained in advance, is obtained
The classification information of the classification of burr indicated by battery pole piece burr areas and battery pole piece burr areas are in the mapping to be checked
The location information of position as in, wherein burr detection model is for characterizing image to be detected and battery pole piece burr areas institute
Corresponding relationship of the classification, battery pole piece burr areas of the burr of instruction between the position in image to be detected.
In some embodiments, training obtains burr detection model as follows: obtaining sample set, wherein sample
Including sample image and sample markup information, sample image includes battery pole piece burr areas, and sample markup information is for indicating
Position of the classification and battery pole piece burr areas of burr indicated by battery pole piece burr areas in sample image；By sample
Sample markup information corresponding with the sample image of input is made in input of the sample image of the sample of concentration as initial model
For the desired output of initial model, training obtains burr detection model.
In some embodiments, initial model includes candidate region network and convolutional neural networks.
In some embodiments, this method further include: the position letter of the classification information and position of storage and/or push classification
Breath.
Second aspect, the embodiment of the present application provide a kind of for detecting the device of battery pole piece burr, which includes:
Acquiring unit is configured to obtain for image captured by battery pole piece as image to be detected；Determination unit is configured to
In response to determining that image to be detected includes battery pole piece burr areas, the class of burr indicated by battery pole piece burr areas is determined
Position of the other and battery pole piece burr areas in image to be detected.
In some embodiments, determination unit is further configured to: image to be detected is input to hair trained in advance
Detection model is pierced, classification information and the battery pole piece burr areas of the classification of burr indicated by battery pole piece burr areas are obtained
The location information of position in image to be detected, wherein burr detection model is for characterizing image to be detected and battery pole piece
Corresponding pass of the classification, battery pole piece burr areas of burr indicated by burr areas between the position in image to be detected
System.
In some embodiments, training obtains burr detection model as follows: obtaining sample set, wherein sample
Including sample image and sample markup information, sample image includes battery pole piece burr areas, and sample markup information is for indicating
Position of the classification and battery pole piece burr areas of burr indicated by battery pole piece burr areas in sample image；By sample
Sample markup information corresponding with the sample image of input is made in input of the sample image of the sample of concentration as initial model
For the desired output of initial model, training obtains burr detection model.
In some embodiments, initial model includes candidate region network and convolutional neural networks.
In some embodiments, device further include: storage unit and/or push unit are configured to store and/or push away
Send the classification information of classification and the location information of position.
The third aspect, the embodiment of the present application provide a kind of server, which includes: one or more processors；
Storage device is stored thereon with one or more programs；When one or more programs are executed by one or more processors, so that
One or more processors realize the method as described in implementation any in first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable medium, are stored thereon with computer program, should
The method as described in implementation any in first aspect is realized when program is executed by processor.
Method and apparatus provided by the embodiments of the present application for detecting battery pole piece burr, it is available to for battery
Image captured by pole piece.If further determining that, captured image includes battery pole piece burr areas, and then can pass through electricity
Pond pole piece burr region determines the classification of burr present in battery pole piece.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that one embodiment of the application can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the method for detecting battery pole piece burr of the application；
Fig. 3 is the schematic diagram according to an application scenarios of the method for detecting battery pole piece burr of the application；
Fig. 4 is the flow chart according to another embodiment of the method for detecting battery pole piece burr of the application；
Fig. 5 is the structural schematic diagram according to one embodiment of the device for detecting battery pole piece burr of the application；
Fig. 6 is adapted for the structural schematic diagram for the computer system for realizing the server of 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 retouched
The specific embodiment stated 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 description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present 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 is shown can be using the application for detecting the method for battery pole piece burr or for detecting battery pole piece
The exemplary architecture 100 of the device of burr.
As shown in Figure 1, system architecture 100 may include server 101, database server 102, network 103 and terminal
Equipment 104,105.Network 103 to server between 101 and terminal device 104,105 provide communication link medium,
Or to provide the medium of communication link between server 101 and database server 102.Network 103 may include each
Kind connection type, such as wired, wireless communication link or fiber optic cables etc..
Terminal device 104,105 is interacted by network 103 with server 101, to receive or send information etc..Terminal device
104, various telecommunication customer end applications, such as the application of information exchange class, the application of image detection class etc. can be installed on 105.
Terminal device 104,105 can be hardware, be also possible to software.It, can be with when terminal device 104,105 is hardware
The various electronic equipments that there is display screen and support image display function, including but not limited to smart phone, tablet computer,
E-book reader, pocket computer on knee and desktop computer etc..It, can be with when terminal device 104,105 is software
It is mounted in above-mentioned cited electronic equipment.Multiple softwares or software module may be implemented into (such as providing distribution in it
Formula service), single software or software module also may be implemented into.It is not specifically limited herein.
Server 101 can be to provide the server of various services.Such as server 101 can be from database server
102 or image capture device (not shown) obtain image, then the image got is handled, and generate processing
As a result.Such as the processing result of generation can also be stored in database server 102 by server 101, or by the place of generation
Reason result is pushed to terminal device 104,105.
Server 101 and database server 102 can be hardware, be also possible to software.When for hardware, it may be implemented
At the distributed server cluster that multiple servers form, individual server also may be implemented into.When for software, it may be implemented
At multiple softwares or software module (such as providing Distributed Services), single software or software module also may be implemented into.
It is not specifically limited herein.
It should be noted that server 101 directly can obtain image from image capture device (not shown), it can also
The processing result of generation is stored in local.At this point it is possible to which database server 102 is not present, terminal can also be not present
Equipment 104,105.
It should be noted that for detecting the method for battery pole piece burr generally by servicing provided by the embodiment of the present application
Device 101 executes, and correspondingly, the device for detecting battery pole piece burr is generally positioned in server 101.
It should be understood that the number of server, network and terminal device in Fig. 1 is only schematical.According to realization need
It wants, can have any number of server, network and terminal device.
With continued reference to Fig. 2, one embodiment of the method for detecting battery pole piece burr according to the application is shown
Process 200.This be used for detect battery pole piece burr method the following steps are included:
Step 201, it obtains for image captured by battery pole piece as image to be detected.
In the present embodiment, for detecting the executing subject (server as shown in Figure 1 of the method for battery pole piece burr
101) it can get by various methods for image captured by battery pole piece, and then the image that will acquire is as to be checked
Altimetric image.
As an example, image capture device can shoot the surface of battery pole piece, then, above-mentioned executing subject can
To obtain captured image as image to be detected from image capture device.It should be noted that image capture device can be with
It is arbitrary, the electronic equipment with image collecting function.
As an example, database server (such as database server 102) can be previously stored with for battery pole piece
Captured image.In turn, above-mentioned executing subject can obtain these images as image to be detected from database server.
Step 202, in response to determining that image to be detected includes battery pole piece burr areas, battery pole piece burr areas is determined
Position of the classification and battery pole piece burr areas of indicated burr in image to be detected.
In the present embodiment, there are burrs on surface of the battery pole piece burr areas for characterizing battery pole piece.In practice, if
There are burrs on the surface of battery pole piece, and image capture device takes the burr on battery pole piece surface, then, it takes
Region corresponding with the burr on battery pole piece surface is exactly battery pole piece burr areas in image.
In the present embodiment, in response to determining that image to be detected includes battery pole piece burr areas, above-mentioned executing subject can
To further determine that the position of the classification and battery pole piece burr areas of battery pole piece burr in image to be detected.
As an example, in practice, technical staff can by a large amount of image including battery pole piece burr areas into
Row processing, and then count and obtain pair between the feature vector of characterization battery pole piece burr areas and the classification of battery pole piece burr
Answer relation table.Wherein, the feature vector of battery pole piece burr areas and the classification of battery pole piece burr are interrelated.Herein,
The classification of battery pole piece burr can be indicated by following any one: number, letter, image etc..
Above-mentioned executing subject can extract several regions from image to be detected, and these regions can be overlapped.Example
Such as, several regions can be extracted from image to be detected by Selective Search algorithm, Edge Boxes algorithm etc..
Then, above-mentioned executing subject can carry out feature extraction to these regions respectively, and generate corresponding feature vector.In turn,
Above-mentioned executing subject can match the feature vector in each region into above-mentioned mapping table respectively.Similarity if it exists
Meet the feature vector of goal-selling (such as similarity is greater than 90%), above-mentioned executing subject can then determine image to be detected packet
Include battery pole piece burr areas.That is, the region in region extracted for image to be detected, if in mapping table
Meet the feature vector of goal-selling in the presence of the similarity of the feature vector with the region, above-mentioned executing subject can be by the region
It is determined as battery pole piece burr areas；It is appreciated that the location of the region can be determined as battery by above-mentioned executing subject
Position of the pole piece burr region in image to be detected.Further, above-mentioned executing subject can will meet the feature of goal-selling
The classification of battery pole piece burr corresponding to vector is determined as the classification of burr indicated by battery pole piece burr areas.
In some optional implementations of the present embodiment, this method further include: the classification of storage and/or push classification
The location information of information and position.
In these implementations, in the classification and battery pole piece burr areas for determining battery pole piece burr in mapping to be checked
After position as in, above-mentioned executing subject can be deposited the location information of the classification information of obtained classification and position
Storage.For example, can store also can store in the local of above-mentioned executing subject communication connection database server (such as
Database server 102).
In these implementations, above-mentioned executing subject can also be by the position of the classification information of obtained classification and position
Information is pushed to the terminal device (such as terminal device 104,105) of communication connection.
It should be noted that above-mentioned classification information can be any letter that the classification of battery pole piece burr is described
Breath, such as " classification 1 ", " classification a " etc..Above-mentioned location information can be characterization battery pole piece burr areas in image to be detected
Position callout box, be also possible to the coordinate on any one vertex of callout box.
With continued reference to the application scenarios that Fig. 3, Fig. 3 are according to the method for detecting battery pole piece burr of the present embodiment
One schematic diagram.In the application scenarios of Fig. 3, when getting for image 301 captured by battery pole piece M, server 300 can
To extract region 302,303,304,305 and 306 from image 301.Then, server 300 can to region 302,303,
304,305 and 306 feature extraction is carried out respectively, obtain corresponding feature vector.
Technical staff can choose a large amount of surface, and there are the battery pole pieces of burr, predefine the class of battery pole piece burr
Not, and acquisition battery pole piece burr image.In turn, the battery pole piece burr areas that acquired image includes is carried out special
Sign is extracted, and corresponding feature vector is obtained.Further, technical staff can make characterization battery pole piece according to statistical result
Mapping table between the feature vector of burr areas and the classification of battery pole piece burr.
This is sentenced for region 306.Server 300 extracts feature to region 306, obtains feature vector A1, A2 and A3.And
Feature vector A1, A2 and A3 for extracting are matched into above-mentioned corresponding relationship afterwards.Similarity meets default mesh if it exists
Region 306 can be determined as battery pole piece burr areas by target feature vector B1, B2 and B3, server 300.Further, it takes
The location of region 306 can be determined as the position of battery pole piece burr areas by business device 300, and will be in mapping table
Classification (i.e. " classification 1 ") corresponding with feature vector B1, B2 and B3 is determined as the classification of burr indicated by region 306.
The method provided by the above embodiment of the application extracts certain amount region first from image to be detected.So
Afterwards, for the region in the region of extraction, following steps are executed respectively: feature extraction being carried out to the region, obtains feature vector；
The feature vector of generation is matched to the mapping table being previously obtained；Similarity meets the feature of goal-selling if it exists
The region is then determined as battery pole piece burr areas by vector, and the location of the region is determined as battery pole piece burr area
Classification corresponding with the feature vector for meeting goal-selling is determined as the classification of burr indicated by the region by the position in domain.
With further reference to Fig. 4, it illustrates the processes of another embodiment of the method for detecting battery pole piece burr
400.This is used to detect the process 400 of the method for battery pole piece burr, comprising the following steps:
Step 401, it obtains for image captured by battery pole piece as image to be detected.
The specific processing of above-mentioned steps 401 and its brought technical effect can be with reference in the corresponding embodiments of Fig. 2
Step 201, details are not described herein.
Step 402, in response to determining that image to be detected includes battery pole piece burr areas, image to be detected is input to pre-
First trained burr detection model, obtains the classification information and battery pole of the classification of burr indicated by battery pole piece burr areas
The location information of position of the piece burr areas in image to be detected.
In the present embodiment, in response to determining that image to be detected includes battery pole piece burr areas, for detecting battery pole
Image to be detected can be input to training in advance by the executing subject (server 101 as shown in Figure 1) of the method for piece burr
Burr detection model, and then obtain the classification information and battery pole piece hair of the classification of burr indicated by battery pole piece burr areas
The location information of position of the spine area domain in image to be detected.Wherein, burr detection model is for characterizing image to be detected and electricity
Pair of the classification, battery pole piece burr areas of burr indicated by the pole piece burr region of pond between the position in image to be detected
It should be related to.
It should be noted that the executing subject of training burr detection model and the method for detecting battery pole piece burr
Executing subject may be the same or different.
In some optional implementations of the present embodiment, burr detection model can be trained as follows
It arrives:
The first step obtains sample set.
Herein, sample includes sample image and sample markup information, and sample image includes battery pole piece burr areas, sample
Classification and battery pole piece burr areas of this markup information for indicating burr indicated by battery pole piece burr areas are in sample
Position in image
The executing subject of training burr detection model can obtain sample set by various methods.For example, working as training sample
When being stored in local, the executing subject of training burr detection model can be directly from the local sample that obtains as sample set.For example,
When training sample is stored in database server (such as database server 102) of communication connection, training burr detects mould
The executing subject of type can also obtain sample as sample set from the database server of communication connection.
Second step, using the sample image of the sample in sample set as the input of initial model, by the sample graph with input
Desired output as corresponding sample markup information as initial model, training obtain burr detection model.
Further, the executing subject of training burr detection model can choose sample from sample set.Then, by selection
Input of the sample image of sample as initial model, using sample markup information corresponding with the sample image of input as initial
The desired output of model, by machine learning method, training obtains burr detection model.
In these implementations, above-mentioned initial model may include candidate region network and convolutional neural networks.
Specifically training step, as described below.
Sample image can be input to convolutional neural networks by the executing subject of step S1, training burr detection model, be obtained
To corresponding characteristic pattern.Wherein, convolutional neural networks may include the various structure sheafs with specific function, such as convolutional layer,
Pond layer, full articulamentum etc..Convolutional layer can extract the feature (such as textural characteristics, edge feature) of sample image.Pond layer
Dimensionality reduction can be carried out to the feature that convolutional layer extracts, and then retains main feature.The master that full articulamentum can will extract
It wants feature to be integrated, and then obtains characteristic pattern.
Step S2, after obtaining characteristic pattern, characteristic pattern can be input to time by the executing subject of training burr detection model
Favored area network then slides sliding window in characteristic pattern, and then certain amount candidate window is extracted in characteristic pattern.
In practice, relevant parameter can be preset, realizes through position of the candidate window in characteristic pattern, is determined in sample image
N candidate region (such as rectangular area), wherein n is positive integer.The every sliding of sliding window is primary as a result, can be in sample
N candidate region is determined in image.In practice, the sliding step of sliding window can be set according to actual needs.
Step S3, after determining candidate region in sample graph, the executing subject of training burr detection model can will be mentioned
The candidate region got is mapped in characteristic pattern.Train the executing subject of burr detection model can be according to candidate region as a result,
Corresponding feature, classifies to object indicated by candidate region (such as battery pole piece burr) in characteristic pattern.Then,
Position in sample image of classification results, candidate region and sample markup information are compared.It in turn, can be from least one
Determine battery pole piece burr areas as object candidate area in a candidate region.
The executing subject of step S4, training burr detection model can determine object candidate area institute according to comparison result
Error between the classification of burr indicated by the classification and sample markup information of the burr of instruction, and determine target candidate area
Position of the battery pole piece burr areas in sample image indicated by position and sample markup information of the domain in sample image
Between error.Further, the sum of above-mentioned two errors can be determined as always accidentally by the executing subject of training burr detection model
Difference.If overall error is less than or equal to default error, it can determine that above-mentioned burr detection model training is completed.
If overall error is greater than default error, the correlation of the adjustable initial model of executing subject of training burr detection model
Parameter.Then using model adjusted as initial model, above-mentioned training step is continued to execute, terminates the item of training until meeting
Part.Wherein, terminate trained condition and include at least one of the following: that the training time reaches preset duration；Frequency of training reaches default
Number；Overall error is less than default error.
Figure 4, it is seen that being used to detect battery pole piece hair in the present embodiment compared with the corresponding embodiment of Fig. 2
The process 400 of the method for thorn highlights the step of the training of burr detection model.The scheme of the present embodiment description can incite somebody to action as a result,
Image to be detected is input to burr detection model trained in advance, so that it is determined that burr indicated by battery pole piece burr areas
The position of classification and battery pole piece burr areas in image to be detected.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides for detecting battery pole
One embodiment of the device of piece burr, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, which specifically may be used
To be applied in various electronic equipments.
As shown in figure 5, the device 500 provided in this embodiment for detecting battery pole piece burr includes acquiring unit 501
With determination unit 502.Wherein, acquiring unit 501 are configured to obtain for image captured by battery pole piece as to be detected
Image；Determination unit 502 is configured in response to determine that image to be detected includes battery pole piece burr areas, determines battery pole
Position of the classification and battery pole piece burr areas of burr indicated by piece burr areas in image to be detected.
In the present embodiment, in the device 500 for detecting battery pole piece burr: acquiring unit 501 and determination unit 502
Specific processing and its brought technical effect can be respectively with reference to the phase of step 201 and step 202 in Fig. 2 corresponding embodiment
It speaks on somebody's behalf bright, details are not described herein.
In some optional implementations of the present embodiment, above-mentioned determination unit 501 can be further configured to: will
Image to be detected is input to burr detection model trained in advance, obtains the classification of burr indicated by battery pole piece burr areas
Position in image to be detected of classification information and battery pole piece burr areas location information, wherein burr detection model
Classification, battery pole piece burr areas for characterizing burr indicated by image to be detected and battery pole piece burr areas is to be checked
The corresponding relationship between position in altimetric image.
In some optional implementations of the present embodiment, training obtains burr detection model as follows: obtaining
Take sample set, wherein sample includes sample image and sample markup information, and sample image includes battery pole piece burr areas, sample
Classification and battery pole piece burr areas of this markup information for indicating burr indicated by battery pole piece burr areas are in sample
Position in image；Using the sample image of the sample in sample set as the input of initial model, by the sample image with input
Desired output of the corresponding sample markup information as initial model, training obtain burr detection model.
In some optional implementations of the present embodiment, initial model includes candidate region network and convolutional Neural net
Network.
In some optional implementations of the present embodiment, above-mentioned apparatus 500 can also be including storage unit (in figure not
Show) and/or push unit (not shown).Wherein, storage unit may be configured to: store classification classification information and
The location information of position；Push unit may be configured to: push the classification information of classification and the location information of position.
The device provided by the above embodiment of the application is clapped firstly, being obtained by acquiring unit 501 for battery pole piece
The image taken the photograph.If determining that captured image includes battery pole piece burr areas by determination unit 502, may further determine that
The classification of burr indicated by battery pole piece burr areas, so that it is determined that the classification of burr present in battery pole piece.
Below with reference to Fig. 6, it illustrates the computer systems 600 for the server for being suitable for being used to realize the embodiment of the present application
Structural schematic diagram.Server shown in Fig. 6 is only an example, should not function and use scope band to the embodiment of the present application
Carry out any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into the program in random access storage device (RAM) 603 from storage section 608 and
Execute various movements appropriate and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
I/O interface 605 is connected to lower component: the importation 606 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 608 including hard disk etc.；
And the communications portion 609 of the network interface card including LAN card, modem etc..Communications portion 609 via such as because
The network of spy's net executes communication process.Driver 610 is also connected to I/O interface 605 as needed.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 610, in order to read from thereon
Computer program be mounted into storage section 608 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 description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 609, and/or from detachable media
611 are mounted.When the computer program is executed by central processing unit (CPU) 601, limited in execution the present processes
Above-mentioned function.
It should be noted that the computer-readable medium of the application can be computer-readable signal media or computer
Readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but it is unlimited
In system, device or the device of --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or any above combination.It calculates
The more specific example of machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, portable of one or more conducting wires
Formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable programmable read only memory
(EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device or
The above-mentioned any appropriate combination of person.In this application, computer readable storage medium can be it is any include or storage program
Tangible medium, which can be commanded execution system, device or device use or in connection.And in this Shen
Please in, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry computer-readable program code.The data-signal of this propagation can take various forms, including but not limited to
Electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable
Any computer-readable medium other than storage medium, the computer-readable medium can send, propagate or transmit for by
Instruction execution system, device or device use or program in connection.The journey for including on computer-readable medium
Sequence code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. are above-mentioned
Any appropriate combination.
The calculating of the operation for executing the application can be write with one or more programming languages or combinations thereof
Machine program code, described program design language include object oriented program language-such as Java, Smalltalk, C+
+, it further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described 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.Described unit also can be set in the processor, for example, can be described as: a kind of processor, packet
Include acquiring unit and determination unit.Wherein, the title of these units does not constitute the limit to the unit itself under certain conditions
It is fixed, for example, acquiring unit is also described as " obtaining for list of the image as image to be detected captured by battery pole piece
Member ".
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in server described in above-described embodiment；It is also possible to individualism, and without in the supplying server.It is above-mentioned
Computer-readable medium carries one or more program, when said one or multiple programs are executed by the server,
So that the server: obtaining for image captured by battery pole piece as image to be detected；In response to determining image to be detected
Including battery pole piece burr areas, classification and the battery pole piece burr areas of burr indicated by battery pole piece burr areas are determined
Position in image to be detected.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
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
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (12)
1. a kind of method for detecting battery pole piece burr, comprising:
It obtains for image captured by battery pole piece as image to be detected；
Include battery pole piece burr areas in response to the described image to be detected of determination, determines indicated by battery pole piece burr areas
Position of the classification and battery pole piece burr areas of burr in described image to be detected.
2. according to the method described in claim 1, wherein, the classification of burr indicated by the determining battery pole piece burr areas
With position of the battery pole piece burr areas in described image to be detected, comprising:
Described image to be detected is input to burr detection model trained in advance, is obtained indicated by battery pole piece burr areas
The location information of position of the classification information and battery pole piece burr areas of the classification of burr in described image to be detected,
In, burr detection model is used to characterize classification, the battery pole of burr indicated by image to be detected and battery pole piece burr areas
Corresponding relationship of the piece burr areas between the position in image to be detected.
3. according to the method described in claim 2, wherein, training obtains the burr detection model as follows:
Obtain sample set, wherein sample includes sample image and sample markup information, and sample image includes battery pole piece burr area
Domain, sample markup information is for indicating that the classification of burr indicated by battery pole piece burr areas and battery pole piece burr areas exist
Position in sample image；
It, will be corresponding with the sample image of input using the sample image of the sample in the sample set as the input of initial model
Desired output of the sample markup information as initial model, training obtain burr detection model.
4. according to the method described in claim 3, wherein, the initial model includes candidate region network and convolutional Neural net
Network.
5. method according to any one of claims 1-4, wherein the method also includes:
Store and/or push the classification information of the classification and the location information of the position.
6. a kind of for detecting the device of battery pole piece burr, comprising:
Acquiring unit is configured to obtain for image captured by battery pole piece as image to be detected；
Determination unit is configured in response to determine that described image to be detected includes battery pole piece burr areas, determines battery pole
Position of the classification and battery pole piece burr areas of burr indicated by piece burr areas in described image to be detected.
7. device according to claim 6, wherein the determination unit is further configured to:
Described image to be detected is input to burr detection model trained in advance, is obtained indicated by battery pole piece burr areas
The location information of position of the classification information and battery pole piece burr areas of the classification of burr in described image to be detected,
In, burr detection model is used to characterize classification, the battery pole of burr indicated by image to be detected and battery pole piece burr areas
Corresponding relationship of the piece burr areas between the position in image to be detected.
8. device according to claim 7, wherein training obtains the burr detection model as follows:
Obtain sample set, wherein sample includes sample image and sample markup information, and sample image includes battery pole piece burr area
Domain, sample markup information is for indicating that the classification of burr indicated by battery pole piece burr areas and battery pole piece burr areas exist
Position in sample image；
It, will be corresponding with the sample image of input using the sample image of the sample in the sample set as the input of initial model
Desired output of the sample markup information as initial model, training obtain burr detection model.
9. device according to claim 8, wherein the initial model includes candidate region network and convolutional Neural net
Network.
10. according to the device any in claim 6-9, wherein described device further include:
Storage unit and/or push unit, be configured to store and/or push the classification classification information and the position
Location information.
11. a kind of server, comprising:
One or more processors；
Storage device is stored thereon with one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as method as claimed in any one of claims 1 to 5.
12. a kind of computer-readable medium, is stored thereon with computer program, wherein the realization when program is executed by processor
Such as method as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810906761.1A CN109064464B (en) | 2018-08-10 | 2018-08-10 | Method and device for detecting burrs of battery pole piece |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810906761.1A CN109064464B (en) | 2018-08-10 | 2018-08-10 | Method and device for detecting burrs of battery pole piece |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109064464A true CN109064464A (en) | 2018-12-21 |
| CN109064464B CN109064464B (en) | 2022-02-11 |
Family
ID=64683305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810906761.1A Active CN109064464B (en) | 2018-08-10 | 2018-08-10 | Method and device for detecting burrs of battery pole piece |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109064464B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109754401A (en) * | 2019-03-15 | 2019-05-14 | 苏州杰锐思自动化设备有限公司 | Lithium battery pole slice burrs on edges on-line measurement device and method |
| CN109886918A (en) * | 2019-01-14 | 2019-06-14 | 广州量子激光智能装备有限公司 | Wire drawing burr detection method, electronic equipment and the storage medium of lithium battery pole slice |
| CN110276156A (en) * | 2019-06-28 | 2019-09-24 | 蜂巢能源科技有限公司 | A kind of negative electrode sheet moisture content detection method and detection device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5544256A (en) * | 1993-10-22 | 1996-08-06 | International Business Machines Corporation | Automated defect classification system |
| CN202824250U (en) * | 2012-09-26 | 2013-03-27 | 万向电动汽车有限公司 | Automatic burr detection device for battery pole piece |
| CN107133629A (en) * | 2016-02-29 | 2017-09-05 | 百度在线网络技术（北京）有限公司 | Picture classification method, device and mobile terminal |
| US20170364798A1 (en) * | 2015-12-22 | 2017-12-21 | Applied Materials Israel Ltd. | Method of deep learning-based examination of a semiconductor specimen and system thereof |
| CN107742128A (en) * | 2017-10-20 | 2018-02-27 | 百度在线网络技术（北京）有限公司 | Method and apparatus for output information |
| CN107966447A (en) * | 2017-11-14 | 2018-04-27 | 浙江大学 | A kind of Surface Flaw Detection method based on convolutional neural networks |
| CN108132054A (en) * | 2017-12-20 | 2018-06-08 | 百度在线网络技术（北京）有限公司 | For generating the method and apparatus of information |
| CN108229364A (en) * | 2017-12-28 | 2018-06-29 | 百度在线网络技术（北京）有限公司 | Contour of building generation method, device, computer equipment and storage medium |
| CN108230317A (en) * | 2018-01-09 | 2018-06-29 | 北京百度网讯科技有限公司 | Steel plate defect detection sorting technique, device, equipment and computer-readable medium |
-
2018
- 2018-08-10 CN CN201810906761.1A patent/CN109064464B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5544256A (en) * | 1993-10-22 | 1996-08-06 | International Business Machines Corporation | Automated defect classification system |
| CN202824250U (en) * | 2012-09-26 | 2013-03-27 | 万向电动汽车有限公司 | Automatic burr detection device for battery pole piece |
| US20170364798A1 (en) * | 2015-12-22 | 2017-12-21 | Applied Materials Israel Ltd. | Method of deep learning-based examination of a semiconductor specimen and system thereof |
| CN107133629A (en) * | 2016-02-29 | 2017-09-05 | 百度在线网络技术（北京）有限公司 | Picture classification method, device and mobile terminal |
| CN107742128A (en) * | 2017-10-20 | 2018-02-27 | 百度在线网络技术（北京）有限公司 | Method and apparatus for output information |
| CN107966447A (en) * | 2017-11-14 | 2018-04-27 | 浙江大学 | A kind of Surface Flaw Detection method based on convolutional neural networks |
| CN108132054A (en) * | 2017-12-20 | 2018-06-08 | 百度在线网络技术（北京）有限公司 | For generating the method and apparatus of information |
| CN108229364A (en) * | 2017-12-28 | 2018-06-29 | 百度在线网络技术（北京）有限公司 | Contour of building generation method, device, computer equipment and storage medium |
| CN108230317A (en) * | 2018-01-09 | 2018-06-29 | 北京百度网讯科技有限公司 | Steel plate defect detection sorting technique, device, equipment and computer-readable medium |
Non-Patent Citations (3)
| Title |
|---|
| 严梁: "基于机器视觉的加热片表面缺陷检测技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 陈海永等: "基于Gabor小波和加权马氏距离的带钢表面缺陷检测", 《电子测量与仪器学报》 * |
| 马岭等: "基于小样本学习的LCD产品缺陷自动检测方法", 《智能系统学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886918A (en) * | 2019-01-14 | 2019-06-14 | 广州量子激光智能装备有限公司 | Wire drawing burr detection method, electronic equipment and the storage medium of lithium battery pole slice |
| CN109754401A (en) * | 2019-03-15 | 2019-05-14 | 苏州杰锐思自动化设备有限公司 | Lithium battery pole slice burrs on edges on-line measurement device and method |
| CN110276156A (en) * | 2019-06-28 | 2019-09-24 | 蜂巢能源科技有限公司 | A kind of negative electrode sheet moisture content detection method and detection device |
| CN110276156B (en) * | 2019-06-28 | 2022-05-03 | 蜂巢能源科技有限公司 | Method and device for detecting moisture content of negative plate |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109064464B (en) | 2022-02-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108154196B (en) | Method and apparatus for exporting image | |
| CN108171191B (en) | Method and apparatus for detecting face | |
| CN107644209A (en) | Method for detecting human face and device | |
| CN109359676A (en) | Method and apparatus for generating vehicle damage information | |
| CN109308490A (en) | Method and apparatus for generating information | |
| CN108986169A (en) | Method and apparatus for handling image | |
| CN109446990A (en) | Method and apparatus for generating information | |
| CN109086780A (en) | Method and apparatus for detecting electrode piece burr | |
| CN109993150A (en) | The method and apparatus at age for identification | |
| CN109063653A (en) | Image processing method and device | |
| CN109255767A (en) | Image processing method and device | |
| CN109376267A (en) | Method and apparatus for generating model | |
| CN110348511A (en) | A kind of picture reproduction detection method, system and electronic equipment | |
| CN109976997A (en) | Test method and device | |
| CN108509921A (en) | Method and apparatus for generating information | |
| CN109901988A (en) | A kind of page elements localization method and device for automatic test | |
| CN110110666A (en) | Object detection method and device | |
| CN109389096A (en) | Detection method and device | |
| CN109285181A (en) | The method and apparatus of image for identification | |
| CN110059624A (en) | Method and apparatus for detecting living body | |
| CN108510084A (en) | Method and apparatus for generating information | |
| CN108446659A (en) | Method and apparatus for detecting facial image | |
| CN109064464A (en) | Method and apparatus for detecting battery pole piece burr | |
| CN108492393A (en) | Method and apparatus for registering | |
| CN108470179A (en) | Method and apparatus for detecting object |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |