CN109583446A - Soil sample box identifying system and method based on artificial neural network - Google Patents
Soil sample box identifying system and method based on artificial neural network Download PDFInfo
- Publication number
- CN109583446A CN109583446A CN201811506506.4A CN201811506506A CN109583446A CN 109583446 A CN109583446 A CN 109583446A CN 201811506506 A CN201811506506 A CN 201811506506A CN 109583446 A CN109583446 A CN 109583446A
- Authority
- CN
- China
- Prior art keywords
- character
- image
- box
- sample box
- segmentation
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 28
- 239000002689 soil Substances 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000011218 segmentation Effects 0.000 claims abstract description 44
- 238000003709 image segmentation Methods 0.000 claims abstract description 23
- 239000000284 extract Substances 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000005303 weighing Methods 0.000 claims description 22
- 238000005070 sampling Methods 0.000 claims description 18
- 238000001914 filtration Methods 0.000 claims description 8
- 238000000926 separation method Methods 0.000 claims 1
- 238000012360 testing method Methods 0.000 abstract description 2
- 239000000523 sample Substances 0.000 description 74
- 238000012545 processing Methods 0.000 description 5
- 239000013068 control sample Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009533 lab test Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/146—Aligning or centring of the image pick-up or image-field
- G06V30/1475—Inclination or skew detection or correction of characters or of image to be recognised
- G06V30/1478—Inclination or skew detection or correction of characters or of image to be recognised of characters or characters lines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Character Discrimination (AREA)
- Character Input (AREA)
Abstract
The present invention relates to soil test apparatus fields, provide a kind of soil sample box identifying system and method based on artificial neural network, comprising: image collecting device, image segmentation device, Character segmentation device and character recognition device；Image collecting device acquires image to the image acquisition region in sample delivery device；Image segmentation device carries out the segmentation of character zone to acquired image, and extracts box region；Character segmentation device carries out pretreatment and Character segmentation to the box region extracted；Character recognition device establishes Character mother plate database by self training, by aspect ratio to identifying character.The present invention replaces human eye to carry out observation identification to sample box number using artificial neural network, network itself can be trained automatically during identification, obtain more excellent recognition result, avoid the error in reading generated when artificial observation, it ensure that the accuracy that box number is read, and improve the mechanization and automation of device.
Description
Technical field
The present invention relates to soil test apparatus fields, know more particularly to a kind of soil sample box number based on artificial neural network
Other system and method.
Background technique
Currently, laboratory used technical method in terms of geotechnical sample raw data acquisition and data processing is excessively former
Begin, needs to carry out the acquisition of initial data by human eye.Soil mechanics laboratory is in the number record and dry and wet for carrying out geotechnical sample
Soil sample will appear the error that box number is manually read during weighing, cause two groups of parallel laboratory tests of a sample originally may
There is the mistake not corresponded to, in terms of box number repetition, is brought a great deal of trouble to the arrangement of later period Earthwork Experiment Data.
Summary of the invention
(1) technical problems to be solved
The object of the present invention is to provide a kind of box automatic recognition system and method based on artificial neural network solve existing
There is the artificial reading box number in technology to be easy to produce error in reading problem.
(2) technical solution
In order to solve the above technical problem, the present invention provides a kind of, and the soil sample box number based on artificial neural network identifies system
System, comprising: image collecting device, image segmentation device, Character segmentation device and character recognition device；Wherein, described image
Acquisition device is right against the image acquisition region of sample box conveying device；Described image segmenting device and described image acquisition device
Connection, for described image acquisition device acquired image to be split, and extracts sample box region；The word
Symbol segmenting device is connect with described image segmenting device, for carrying out the box sign character region of the sample box region
Pretreatment and Character segmentation；The character recognition device is connect with the Character segmentation device, the box number after dividing for identification
Character.
Wherein, further include host and controller, the controller respectively with the sample box conveying device, image collector
Set, image segmentation device, Character segmentation device and character recognition device connection, for control the sample box conveying device,
The working condition of image collecting device, image segmentation device, Character segmentation device and character recognition device, the host and institute
Character recognition device connection is stated, the box sign character of identification is received.
It wherein, further include weighing device, the weighing device is installed on the bottom of the sample box conveying device, and is located at
The rear of described image acquisition device weighs to sample for identification after the box sign character after segmentation, the host and institute
Weighing device connection is stated, the weight that weighing device is measured is received.
Wherein, further include separating device, the separating device is installed on the sample box conveying device, and with the control
Device connection, is controlled by the controller, single sample is made to be delivered to image acquisition region.
Wherein, the separating device is several scraper plates, and the scraper plate level is placed equidistant with to convey in the sample box and fill
The top set.
Wherein, further include sampling device and sampling device, the sampling device are set to entering for the sample box conveying device out
Mouthful place, and connect with the controller, the sampling device out set on the exit of the sample box conveying device, and with the control
Device connection processed.
The soil sample box recognition methods based on artificial neural network that invention additionally discloses a kind of, comprising:
Image collecting device acquires image to the image acquisition region in sample box conveying device；
Image segmentation device carries out the segmentation of character zone to the image that image acquisition device arrives, and extracts box institute
In region；
The box region that Character segmentation device extracts image segmentation device carries out pretreatment and Character segmentation；
Character recognition device passes through self training first and establishes 26 letters and 10 digital Character mother plate databases, leads to
It crosses aspect ratio and identifies character that Character segmentation device is partitioned by sequence.
Wherein, further includes: the sample after identiflication number is weighed and recorded.
Wherein, the pretreatment includes: the box region that Character segmentation device first extracts image segmentation device
Slant Rectify is carried out, so that box sign character is in horizontality, then is split.
Wherein, Character segmentation device is calculated using gaussian filtering and gradient filtering, the region after obtaining binaryzation, by two-value
Region after change is rotated, so that box sign character is in horizontality.
(3) beneficial effect
A kind of soil sample box identifying system based on artificial neural network provided by the invention, utilizes artificial neural network generation
Intelligent recognition is carried out to sample box number for human eye, the error generated when avoiding manually reading ensure that the accuracy that box number is read,
And improve the mechanization and automation of device.
Detailed description of the invention
Fig. 1 is that the present invention is based on the structural schematic diagrams of the soil sample box identifying system of artificial neural network；
Fig. 2 is the image procossing recognition subsystem structural schematic diagram in the present invention；
In figure, 1, sample box conveying device；2, image procossing recognition subsystem；21, image collecting device；22, image point
Cut device；23, Character segmentation device；24, character recognition device；3, host and controller；4, weighing device；5, scraper plate；6, into
Sampling device；7, go out sampling device.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Following instance
For illustrating the present invention, but it is not intended to limit the scope of the invention.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection or integral type connects；It can
To be mechanical connection, it is also possible to be electrically connected；It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
Concrete meaning in invention.
As depicted in figs. 1 and 2, the present invention discloses a kind of box automatic recognition system based on artificial neural network, special
Sign is, comprising: image collecting device 21, image segmentation device 22, Character segmentation device 23 and character recognition device 24；Its
In, described image acquisition device 21 is right against the image acquisition region of sample box conveying device 1；Described image segmenting device 22 with
Described image acquisition device 21 connects, and for 21 acquired image of described image acquisition device to be split, and extracts sample
Product box region；The Character segmentation device 23 is connect with described image segmenting device 22, is used for the sample box number
The box sign character region of region carries out pretreatment and Character segmentation；The character recognition device 24 is filled with the Character segmentation
23 connections are set, the box sign character after dividing for identification.
Specifically, sample box conveying device 1 of the invention carries out the conveying of sample using conveyer belt, by image collecting device
The suitable image acquisition region of 21 alignment conveyer belts, the selection of image acquisition region can close on the feed end of conveyer belt.
Image collecting device 21 can be used the first-class filming instrument of digital vedio recording and carry out Image Acquisition to image acquisition region.Image collector
Set 21 and acquired image be transferred to image segmentation device 22, image segmentation device 22 using Matlab software programming or other
Software is separated according to sample box with the color gradient of ambient enviroment, determines sample box region, Character segmentation device
23 pairs of character zones carry out pretreatment and Character segmentation, and the box sign character after 24 pairs of last character identification device segmentations is known
Not, the box sign character of identification host is transferred to save.As depicted in figs. 1 and 2, image collecting device 21 of the invention,
Image segmentation device 22, Character segmentation device 23 and character recognition device 24 are integrated in image procossing recognition subsystem 2.
It is possible to further install optical sensor on digital camera head, whether the sample detected on conveyer belt enters
Into image acquisition areas, in addition if necessary to light filling, then light source can be added, control intensity of illumination.And for image acquisition areas
The same sample in domain carries out multiple Image Acquisition, carries out repeatedly identification judgement, increases accuracy of identification and reliability, the present embodiment pair
In same sample Image Acquisition number be three times.The present embodiment guarantees sample box image precise acquisition by operation above.
A kind of soil sample box identifying system and method based on artificial neural network provided by the invention, utilizes artificial neuron
Network replaces human eye to carry out intelligent recognition to sample box number, and the error generated when avoiding manually reading ensure that box number was read
Accuracy, and improve the mechanization and automation of device.
Wherein, further include host and controller 3, the controller respectively with the sample box conveying device 1, Image Acquisition
Device 21, image segmentation device 22, Character segmentation device 23 and character recognition device 24 connect, for controlling the sample box
The work of conveying device 1, image collecting device 21, image segmentation device 22, Character segmentation device 23 and character recognition device 24
Make state, the host is connect with the character recognition device 24, receives the box sign character of identification.The controller of the present embodiment is used
In the transport status of control sample box conveying device, its adjustable conveying speed, controller also can control artificial neural network
All parts working condition, such as: when sample box reach image acquisition region after, control image collecting device 21 to the area
Domain carries out acquisition of taking pictures, and controls its subsequent image processing flow, the final box number for identifying corresponding region.As shown in Figure 1, this
The host and controller 1 of embodiment are integrally disposed.
It wherein, further include weighing device 4, the weighing device 4 is installed on the bottom of the sample box conveying device, and position
In the rear of described image acquisition device, for identification divide after box sign character after, weigh to sample, the host with
The weighing device connection, receives the weight that weighing device is measured, and realizes the unification of sample number into spectrum and weight.In the present embodiment
Weighing device 4 is increased, can be weighed to by the sample of the region conveyer belt, and the weight measured can be transmitted
It is received to host, guarantees that sample number into spectrum is corresponded with the weight measured, host stores sample box information and counter sample
Weight, realization automatically extract sample box number and check weighing.Electronic scale etc. can be used in the weighing device 4 of the present embodiment.Preferably, also
Including weighing device platform, the weighing device platform is located at the latter half of sample box conveying device, and the weighing device 4 is put
It is placed on weighing device platform.
Wherein, further include separating device, the separating device is installed on the sample box conveying device 1, and with the control
Device connection processed, is controlled by the controller, single sample is made to be delivered to image acquisition region, guarantees to enter image acquisition region
Sample box is only one, and the image of other sample boxes is avoided to be arrived by image acquisition device, leads to Image Acquisition mistake.It is preferred that
Ground, the separating device are several scraper plates 5, and 5 level of scraper plate is placed equidistant in the top of the sample box conveying device,
As shown in Figure 1, the vertical baffle quantity of the present embodiment is four.By the way that the spacing of adjacent scraper plate 5 on a moving belt, control is arranged
Device control driving sample box conveying device 1 stepper motor pulse signal duration, it can be achieved that fixed range transmission, and then will
Simple sample is transferred to image acquisition region.
Wherein, further include sampling device 6 and sampling device 7, the sampling device 6 are set to the sample box conveying device 1 out
Inlet, and connect with the controller, it is described go out sampling device 7 be set to the exit of the sample box conveying device 1, and with
The controller connection.To sampling device 6 and out, sampling device 7 controls the present embodiment controller, and control sample box enters
Sample box conveying device 1 and from sample box conveying device 1 export.Sampling device 6 in the present embodiment and out sampling device 7 can be with
For conveying devices such as conveyer belt or drag conveyors.It preferably, further include buffer board, the buffer board is connected to the sample dress out
It sets between 7 and the weighing device 4.
Invention additionally discloses a kind of box automatic identifying methods of artificial neural network, comprising:
Image collecting device acquires image to the image acquisition region in sample box conveying device；
Image segmentation device carries out the segmentation of character zone to the image that image acquisition device arrives, and extracts box institute
In region；
The box region that Character segmentation device extracts image segmentation device carries out pretreatment and Character segmentation；
Character recognition device passes through self training first and establishes 26 letters and 10 digital Character mother plate databases, leads to
It crosses aspect ratio and identifies character that Character segmentation device is partitioned by sequence.
Wherein, further includes: the sample after identiflication number is weighed and recorded.
Wherein, the pretreatment includes: the box region that Character segmentation device first extracts image segmentation device
Slant Rectify is carried out, so that box sign character is in horizontality, then is split.
Wherein, Character segmentation device is calculated using gaussian filtering and gradient filtering, the region after obtaining binaryzation, by two-value
Region after change is rotated, so that box sign character is in horizontality.
Specifically, image collecting device can be the camera installation of camera, DV or mobile phone etc., image is adopted
Collect region and carries out Image Acquisition.When sample box is in image acquisition region, controller control sample delivery device shuts down,
When guaranteeing that image collecting device takes pictures to sample box, sample is remain stationary.For single one sample, image collecting device pair
It at least acquires three images, it is ensured that the accuracy of Image Acquisition.For the image that image acquisition device arrives, image segmentation
Device can first be carried out gray processing processing, i.e., convert gray scale picture for collected color image, carry on the back after treatment
Scenery is generally white, and box sign character is generally black, saves memory space.Further, according to box region and ambient enviroment
Color gradient, image is split, extract box region.Edge detection, gaussian filtering and gradient are carried out to image
The processing such as filtering, the image-region after obtaining a binaryzation, in order to be corrected to acquired image, using linear fit
Method, specifically using random operator to image progress rectification and vertical correction, so-called bianry image refer generally to a width
Image is only black in complete image, white two-value, and key is rationally to determine threshold values, separating background, character.It is handled through system
The image improved shape stability crossed not will form vacancy or lose useful shape information.The key of threshold process is to generate threshold value,
Threshold value can be generated by calculating method, can also be specified by user, it is assumed that threshold value is greater than the pixel grey scale of figure, then needs the gray scale the pixel
It is set as 0 or 255, if the gray value of pixel is greater than threshold value, is arranged to 255 or 0, it in this way can be by the box sign character of black
Divide and extract from the background of white, finally the character extracted is identified by character recognition device.Pass through
Sample training neural network identifies box sign character on this basis.Its detailed process is as follows, trains four sub-networks first: its
One Chinese character；Secondly alphabetical；Thirdly alphanumeric；Its four number, and obtain corresponding weight, number of nodes.Pretreatment is a large amount of
Specific box image, successively extracts characteristics of image, and read the weight in file, number of nodes, guarantees box image and box number
Character corresponds, and uploads to host, determines that box image is corresponding with which box sign character.The box that finally needs are identified
Number image finds corresponding box sign character in host, and final output completes identification.Finally, the sample after identifying will be completed
Product are weighed, and weight information is also uploaded to host, correspond example weight and number, are completed box number identification and are claimed
It operates again, repeats above step, box number identification and samples weighing are carried out to next sample box.
A kind of soil sample box identifying system method based on artificial neural network provided by the invention, utilizes artificial neural network
Network replaces human eye to carry out intelligent recognition to sample box box number, and the error generated when avoiding manually reading ensure that box number was read
Accuracy, and improve the mechanization and automation of device.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of soil sample box identifying system based on artificial neural network characterized by comprising image collecting device, figure
As segmenting device, Character segmentation device and character recognition device；Wherein, described image acquisition device is right against sample box conveying
The image acquisition region of device；Described image segmenting device is connect with described image acquisition device, for acquiring described image
Device acquired image is split, and extracts sample box region；The Character segmentation device and described image point
Device connection is cut, for the box sign character region of the sample box region to be carried out pretreatment and Character segmentation；It is described
Character recognition device is connect with the Character segmentation device, the box sign character after dividing for identification.
2. the soil sample box identifying system based on artificial neural network as described in claim 1, which is characterized in that further include master
Machine and controller, the controller respectively with the sample box conveying device, image collecting device, image segmentation device, character
Segmenting device and character recognition device connection, for controlling the sample box conveying device, image collecting device, image segmentation
The working condition of device, Character segmentation device and character recognition device, the host connect with the character recognition device, connect
Receive the box sign character of identification.
3. the soil sample box identifying system based on artificial neural network as claimed in claim 2, which is characterized in that further include claiming
Refitting is set, and the weighing device is installed on the bottom of the sample box conveying device, and after described image acquisition device
Side weighs to sample for identification after the box sign character after segmentation, and the host is connect with the weighing device, receives
The weight that weighing device is measured.
4. the soil sample box identifying system based on artificial neural network as claimed in claim 2, which is characterized in that further include point
Every device, the separating device is installed on the sample box conveying device, and connect with the controller, by the controller control
System, makes single sample be delivered to image acquisition region.
5. the soil sample box identifying system based on artificial neural network as claimed in claim 4, which is characterized in that the separation
Device is several scraper plates, and the scraper plate level is placed equidistant in the top of the sample box conveying device.
6. the soil sample box identifying system based on artificial neural network as claimed in claim 3, which is characterized in that further include into
Sampling device and out sampling device, the sampling device is set to the inlet of the sample box conveying device, and connects with the controller
It connects, the sampling device out is set to the exit of the sample box conveying device, and connect with the controller.
7. a kind of soil sample box recognition methods based on artificial neural network characterized by comprising
Image collecting device acquires image to the image acquisition region in sample box conveying device；
Image segmentation device carries out the segmentation of character zone to the image that image acquisition device arrives, and extracts box location
Domain；
The box region that Character segmentation device extracts image segmentation device carries out pretreatment and Character segmentation；
Character recognition device passes through self training first and establishes 26 letters and 10 digital Character mother plate databases, passes through spy
Sign comparison is identified the character that Character segmentation device is partitioned by sequence.
8. the soil sample box recognition methods based on artificial neural network as claimed in claim 7, which is characterized in that further include:
Sample after identiflication number is weighed and recorded.
9. the soil sample box recognition methods based on artificial neural network as claimed in claim 7, which is characterized in that the pre- place
Reason includes: that Character segmentation device first carries out Slant Rectify to the box region that image segmentation device extracts, so that box number
Character is in horizontality, then is split.
10. the soil sample box recognition methods based on artificial neural network as claimed in claim 9, which is characterized in that character point
Device to be cut to calculate using gaussian filtering and gradient filtering, the region after obtaining binaryzation rotates the region after binaryzation,
So that box sign character is in horizontality.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811506506.4A CN109583446A (en) | 2018-12-10 | 2018-12-10 | Soil sample box identifying system and method based on artificial neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811506506.4A CN109583446A (en) | 2018-12-10 | 2018-12-10 | Soil sample box identifying system and method based on artificial neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109583446A true CN109583446A (en) | 2019-04-05 |
Family
ID=65928743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811506506.4A Pending CN109583446A (en) | 2018-12-10 | 2018-12-10 | Soil sample box identifying system and method based on artificial neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109583446A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112967000A (en) * | 2021-03-11 | 2021-06-15 | 中工美(北京)供应链物流管理有限责任公司 | Appearance and weight identification method of silver storage automatic warehousing system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1815510A (en) * | 2006-02-28 | 2006-08-09 | 吴建国 | Electronic ballot box based on image-symbol identification |
| CN102507255A (en) * | 2011-10-10 | 2012-06-20 | 中国农业大学 | RFID-based soil sampling and automatic marking device |
| CN103377498A (en) * | 2012-04-25 | 2013-10-30 | 崔岩 | Cloud-architecture electronic water-gate management system and method |
| CN103818675A (en) * | 2013-11-07 | 2014-05-28 | 唐山创通科技有限公司 | RFID (radio frequency identification device) intelligent identification tray system |
| CN104573688A (en) * | 2015-01-19 | 2015-04-29 | 电子科技大学 | Mobile platform tobacco laser code intelligent identification method and device based on deep learning |
| CN104700510A (en) * | 2015-03-17 | 2015-06-10 | 苏州长鼎兴智能科技有限公司 | Intelligent express box system and delivery method |
| CN107194299A (en) * | 2017-07-11 | 2017-09-22 | 余军辉 | A kind of label recognition system classified for heparin tube |
| CN107748115A (en) * | 2017-08-20 | 2018-03-02 | 中国铁路设计集团有限公司 | Geotechnical Engineering soil sample box is weighed automatically and the system and method for numbering automatic identification |
| CN108596166A (en) * | 2018-04-13 | 2018-09-28 | 华南师范大学 | A kind of container number identification method based on convolutional neural networks classification |
-
2018
- 2018-12-10 CN CN201811506506.4A patent/CN109583446A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1815510A (en) * | 2006-02-28 | 2006-08-09 | 吴建国 | Electronic ballot box based on image-symbol identification |
| CN102507255A (en) * | 2011-10-10 | 2012-06-20 | 中国农业大学 | RFID-based soil sampling and automatic marking device |
| CN103377498A (en) * | 2012-04-25 | 2013-10-30 | 崔岩 | Cloud-architecture electronic water-gate management system and method |
| CN103818675A (en) * | 2013-11-07 | 2014-05-28 | 唐山创通科技有限公司 | RFID (radio frequency identification device) intelligent identification tray system |
| CN104573688A (en) * | 2015-01-19 | 2015-04-29 | 电子科技大学 | Mobile platform tobacco laser code intelligent identification method and device based on deep learning |
| CN104700510A (en) * | 2015-03-17 | 2015-06-10 | 苏州长鼎兴智能科技有限公司 | Intelligent express box system and delivery method |
| CN107194299A (en) * | 2017-07-11 | 2017-09-22 | 余军辉 | A kind of label recognition system classified for heparin tube |
| CN107748115A (en) * | 2017-08-20 | 2018-03-02 | 中国铁路设计集团有限公司 | Geotechnical Engineering soil sample box is weighed automatically and the system and method for numbering automatic identification |
| CN108596166A (en) * | 2018-04-13 | 2018-09-28 | 华南师范大学 | A kind of container number identification method based on convolutional neural networks classification |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112967000A (en) * | 2021-03-11 | 2021-06-15 | 中工美(北京)供应链物流管理有限责任公司 | Appearance and weight identification method of silver storage automatic warehousing system |
| CN112967000B (en) * | 2021-03-11 | 2024-10-15 | 中工美(北京)供应链物流管理有限责任公司 | Appearance and weight identification method of automatic warehouse-in system for silver warehouse |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108596046A (en) | A kind of cell detection method of counting and system based on deep learning | |
| CN109344894A (en) | Garbage classification recognition methods and device based on Multi-sensor Fusion and deep learning | |
| CN104155312B (en) | Grain intragranular portion pest detection method and apparatus based on near-infrared computer vision | |
| CN106127780A (en) | A kind of curved surface defect automatic testing method and device thereof | |
| CN105388162B (en) | Raw material silicon chip surface scratch detection method based on machine vision | |
| CN110414334A (en) | A kind of smart water quality recognition methods maked an inspection tour based on unmanned plane | |
| CN106803248B (en) | Fuzzy license plate image blur evaluation method | |
| CN104198324B (en) | Computer vision-based method for measuring proportion of cut leaves in cut tobacco | |
| CN109255787A (en) | Silk ingot scratch detection system and method based on deep learning and image processing techniques | |
| CN104637058B (en) | A kind of volume of the flow of passengers identify statistical methods based on image information | |
| CN101930533B (en) | Device and method for performing sky detection in image collecting device | |
| CN105251707B (en) | Bad part eject sorting equipment based on medical large transfusion visible foreign matters detecting system | |
| CN103984979B (en) | The algae automatic detection counting device and method being imaged without Lenses Diffractive | |
| CN112069985B (en) | High-resolution field image rice spike detection and counting method based on deep learning | |
| CN108921099A (en) | Moving ship object detection method in a kind of navigation channel based on deep learning | |
| FI67043C (en) | ADJUSTMENT OF THE CLASSIFICATION OF STYCLES AND BEARING SIGNS | |
| CN111161214B (en) | System and method for measuring pig weight and identifying drinking behavior based on binocular vision | |
| CN107944504A (en) | Plank identifies and machine learning method, device and the electronic equipment of plank identification | |
| CN103487104A (en) | System and method for collecting and identifying images of capillary pipe liquid level type data | |
| CN111652883B (en) | Glass surface defect detection method based on deep learning | |
| CN109064449B (en) | Method for detecting bridge surface diseases | |
| CN108267455A (en) | plastic film printing character defect detecting device and method | |
| CN106248680A (en) | A kind of engine commutator quality detecting system based on machine vision and detection method | |
| CN110096980A (en) | Character machining identifying system | |
| CN110427943A (en) | A kind of intelligent electric meter technique for partitioning based on R-CNN |
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: 20190405 |