CN107862234A - A kind of recognition methods of color bar code, electronic equipment and storage medium - Google Patents
A kind of recognition methods of color bar code, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN107862234A CN107862234A CN201710996010.9A CN201710996010A CN107862234A CN 107862234 A CN107862234 A CN 107862234A CN 201710996010 A CN201710996010 A CN 201710996010A CN 107862234 A CN107862234 A CN 107862234A
- Authority
- CN
- China
- Prior art keywords
- bar code
- image
- color
- recognition methods
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of recognition methods of color bar code, comprise the following steps:As a result obtaining step:Extract the color value of all color lumps in bar code region, and according to barcode encoding rule with character information corresponding to each color lump in bar code region, each color lump is arranged in order in order in the bar code region, character information and color value is corresponded to form barcode encoding rule.The invention also discloses a kind of electronic equipment and storage medium.The recognition methods of the color bar code of the present invention by the extraction to color lump color in bar code region, and according to barcode encoding rule with character corresponding to bar code region;So that the present invention can identify colour barcode, and batch processing can be carried out to colour barcode.
Description
Technical field
The present invention relates to a kind of Bar Code field, more particularly to a kind of recognition methods of color bar code, electronics
Equipment and storage medium.
Background technology
At present, with the expansion and development at full speed of retail business and consumption market, increasing place needs to use label
And bar code.
Existing bar code is mainly to be worked out based on the empty border of bar and width using the principle of colour contrast, so existing
There is the recognition mode of bar code, its principle is also predominantly distinguished by the empty border of bar and width is differentiated, and being broadly divided into makes
Distinguished with professional bar code scan equipment and camera.Professional bar code scan equipment is by scanning device sensitivity and distance
Have a great influence.And the mode of bar code reading is carried out using camera, its method is entered using the mode of two-value method or gray scale
The identification of row bar code, this mode are all to have abandoned color in fact, are only capable of entering the bar code made based on black and white contrast principle
Row identification, and None- identified really passes through the different colour barcodes for carrying out bar code establishment of color value.And current black and white bar shaped
Code and Quick Response Code can not carry out high-volume identification.
So existing barcode recognition equipment and method are invalid to colour barcode, the knowledge of colour barcode can not be carried out
Not.
The content of the invention
For overcome the deficiencies in the prior art, an object of the present invention is to provide a kind of identification side of color bar code
Method, it can solve the technical problem of colour barcode identification.
The second object of the present invention is to provide a kind of electronic equipment, and it can solve the technical problem of colour barcode identification.
The third object of the present invention is to provide a kind of computer-readable recording medium, and it can solve colour barcode identification
Technical problem.
An object of the present invention adopts the following technical scheme that realization:
A kind of recognition methods of color bar code, comprises the following steps:
As a result obtaining step:Extract the color value of all color lumps in bar code region, and according to barcode encoding rule with bar
Character information corresponding to each color lump in code region, each color lump is arranged in order in order in the bar code region, by character information with
Color value is corresponded to form barcode encoding rule.
Further, it is further comprising the steps of before result obtaining step:
Image acquisition step:Current image information is obtained, described image information includes at least one bar code image;
Image confirming step:Current image information is compared to obtain bar code region with bar code identification model.
Further, image preprocessing step is also included after image acquisition step:To the current image got
Information is pre-processed, and the pretreatment includes removing noise and interference, image cutting and image normalization.
Further, 3D aligning steps are also included after image confirming step:To bar code region carry out 3D corrections so that
Obtain the bar code region and be adjusted to rectangle bar code region.
Further, the process of establishing of the bar code identification model includes following sub-step:
Model preprocessing step:The training bar code image got is pre-processed, the pretreatment includes removal and made an uproar
Sound and interference, image cutting and image normalization;
Characteristic extraction step:Feature extraction is carried out to obtain bar code training set to pretreated training bar code image;
Model establishment step:Extraction standard template is to establish bar code identification model from bar code training set.
Further, the training bar code image includes colour barcode, black and white bar code and Quick Response Code.
Further, character check step is also included after result obtaining step:According to verification rule to the character
Information is verified to confirm whether it is correct.
Further, information forwarding step is also included after character check step:Character information after verification is sent out
Display module is delivered to be shown or send the character information after verification to data processing module to be handled.
Further, 3D aligning steps are also included after image confirming step:To bar code region carry out 3D corrections so that
It is rectangle bar code region to obtain the bar code region.
The second object of the present invention adopts the following technical scheme that realization:
A kind of electronic equipment, including memory, processor and storage can be run on a memory and on a processor
Computer program, the colored bar shaped in one of the object of the invention described in any one is realized during the computing device described program
Code recognition methods.
The third object of the present invention adopts the following technical scheme that realization:
A kind of computer-readable recording medium, is stored thereon with computer program, and the computer program is held by processor
The method as described in one of the object of the invention any one is realized during row.
Compared with prior art, the beneficial effects of the present invention are:
The recognition methods of the color bar code of the present invention is by the extraction to color lump color value in bar code region, and according to bar
Code coding rule with character corresponding to bar code region;So that the present invention can identify colour barcode, and can be to coloured silk
Vitta code carries out batch processing.
Brief description of the drawings
Fig. 1 is the flow chart of the recognition methods of the color bar code of the present invention.
Embodiment
Below, with reference to accompanying drawing and embodiment, the present invention is described further, it is necessary to which explanation is, not
Under the premise of afoul, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example.
The present invention by:The several part compositions of acquisition module, identification module, data module, display module, functions are such as
Under:
Acquisition module:Acquisition module is shot by camera to bar code, is obtained bar code image and is sent to identification mould
Block.Support to obtain one or more bar code images simultaneously.
Identification module:The bar code image that acquisition module is sent is received, row information identification is entered to bar code image.
Data module:Preserve coding rule, the barcode database of content information of all kinds bar code.
Display module:According to bar code recognition result and barcode types, the bar code content information in called data module is gone forward side by side
Row display.
Present embodiment discloses a kind of electronic equipment, including memory, processor and storage are on a memory and can be
The computer program run on processor, as shown in figure 1, realizing following steps during the computing device described program:
S1:Current image information is obtained, described image information comprises at least a bar code image;By camera to bar
Code is shot, and the image information got is sent into identification module.Support to obtain one or more bar code images simultaneously;
This step when being obtained, is not limited to only obtain a bar code primarily to getting needs the image that identifies,
It can be that multiple bar codes are handled, if there is individual bar code more than 30 in piece image, pass through the recognition methods of the present invention
Also it can be identified accordingly;
S2:Current image information is pre-processed;The image information of acquisition is pre-processed;It is main to include removing
The preprocessing process such as noise and interference, image cutting, normalization, by pre-processing the processing identity for improving server to image
Energy.
S3:Pretreated current image information is compared to obtain bar code region with bar code identification model;Here
Bar code region include the information that the positional information of bar code and bar code are included in itself, such as bar code starting position, stop bits
The directional information put;Bar code region can be positioned by comparing to obtain bar code region, the bar code identification model is built
It is vertical to include following sub-step:By machine learning largely various angle shots arrive, the bar code image of various forms, type,
Establish bar code identification model.Obtained because existing bar code includes all kinds such as bar code, Quick Response Code, colour barcode, during study
A large amount of above-mentioned various types of bar code images are trained, the identification model of all types of bar codes of correspondence establishment.Model establishes mesh
Be to differentiate in the image got either with or without information such as the directions of type and bar code of bar code and bar code.So sentencing
When disconnected, the image of the bar code comprising multiple types simultaneously can be judged simultaneously, and all types of bar code images are carried out positioning and
Correction.
Model preprocessing step:The training bar code image got is pre-processed;The training bar code image includes
Colour barcode, black and white bar code and Quick Response Code;All types of bar code images are pre-processed, by removing noise and interference, image
The preprocessing process such as cutting, normalization improve the performance that server identifies to image procossing.Except the coloured silk cited by the present embodiment
Outside the identification method of vitta code, the identification of black and white bar code and Quick Response Code mode can also be carried out, to only including black and white bar code, two
When the bar code image of dimension code is identified, image binaryzation processing can also be carried out in image preprocessing, to improve server
To the speed of bar code identifying processing.
Characteristic extraction step:Feature extraction is carried out to obtain bar code training set to pretreated training bar code image;It is right
Pretreated bar code image carries out feature extraction, according to the color of the space density of different bar code images, pattern arrangement situation
Feature, bar code image is divided into 5*5 25 grid spaces, the points calculated in each grid always count it with bar code image
Than obtaining 25 dimensional feature vectors.
Model establishment step:Extraction standard template is to establish bar code identification model from bar code training set.By knowing repeatedly
Do not train, standard masterplate is extracted from each bar code image of training set, establish standard feature storehouse, complete building for bar code identification model
It is vertical.Each type of bar code has hundreds of standard masterplates needed because bar code has a directionality, during training by bar code image by
Prime direction carries out being supplied to machine to be learnt after correctly arranging, after pretreatment, feature extraction, by all kinds of bars of training set
In the characteristic vector deposit file of code.Need to indicate the right value of all kinds of bar codes during training.
S31:3D corrections are carried out to bar code region to cause the bar code region as rectangle bar code region;Matching identification model is sentenced
The each bar code image region included in disconnected picture, according to the bar code region judged, each bar code image is positioned,
3D is corrected and barcode types judge.
Bar code positioning:Feature extraction is carried out to pretreated bar code image, searches out and forms colour barcode with notable
The attributes such as the color of feature, pattern, shape, calculate their geometric feature, and passing through these characteristic quantities, to form description colored
The characteristic vector of bar code, it is compared with the characteristic vector of the bar code identification model established in system, when similarity exceedes
80% is determined as a bar code region, and the bar code region is positioned according to judged result.
3D is corrected:During due to shooting, where shooting angle, bar code are pasted the problems such as the angles of article, bar code image
A certain degree of scalloping generally be present or angle rotation is reverse, it is therefore desirable to which 3D corrections are carried out to single bar code image.It is logical
Space reflection is crossed, is projected after four points at single four angles in bar code upper and lower, left and right are fixed, single bar code image is entered
Line direction rotation, skew control, make bar code image be arranged as the rectangular area of standard according to bar code prime direction, obtain standard
The single bar code image of shape size;So that the degree of accuracy of identification greatly increases;
S4:The color value of all color lumps in bar code region is extracted, it is assorted in bar code region to obtain according to barcode encoding rule
Character information corresponding to block, each color lump is arranged in order in order in the bar code region, by a pair of character information and color value 1
Should be regular to form barcode encoding;
S5:The character information is verified according to verification rule to confirm whether it is correct;The verification rule that is to say
Check code sets rule, and because each colour barcode has a bit check code, this check code can be according to above
What data obtained, so it can not only be shown by color, can also be obtained by calculating, what is tested
When, can by calculate the corresponding character of the check code be compared with the character corresponding to the color value recognized with up to
To the purpose of checking character information;
S6:Character information after verification, which is sent to display module, to be shown or is sent out the character information after verification
Data processing module is delivered to be handled.Bar code information identifies:Each type of bar code has fixed coding rule, according to
Single bar code image and corresponding barcode types after positioning, 3D corrections, the volume of the type bar code is corresponded in called data module
Code rule carries out bar code information identification.After identification for colour barcode is, it is necessary to which the color value to each stick judges, root
Judge character information corresponding to the color value according to coding rule, and judged result is verified according to verification rule.By testing
Card, then be sent to display module by recognition result, carry out the data processing or displaying of next step.
The identification process on color bar code of the present invention is as follows:
After being corrected by pretreatment, feature extraction, Bar code positioning and 3D, matching identification model, we can determine whether out this
The type of code is color bar code.
According to the coding rule of colour barcode, the colour barcode is to represent each using wide a variety of colors block to correspond to
Bar, NUL.After taking color average to each stick of the colour barcode, the HSB color value informations of each stick are extracted, it is right
Coding rule is answered to obtain character information corresponding to the color value of each, wherein HSB color values are corresponding with rgb value, so
Here can also be carried out by the way of rgb value.
The recognition result of bar code is verified according to regular and each corresponding character identification result of verification, to ensure
The correctness of recognition result.
Above-mentioned embodiment is only the preferred embodiment of the present invention, it is impossible to the scope of protection of the invention is limited with this,
The change and replacement for any unsubstantiality that those skilled in the art is done on the basis of the present invention belong to institute of the present invention
Claimed scope.
Claims (10)
1. a kind of recognition methods of color bar code, it is characterised in that comprise the following steps:
As a result obtaining step:Extract the color value of all color lumps in bar code region, and according to barcode encoding rule with bar code area
Character information corresponding to each color lump in domain, each color lump is arranged in order in order in the bar code region, by character information and color
Value is corresponded to form barcode encoding rule.
2. the recognition methods of color bar code as claimed in claim 1, it is characterised in that also wrapped before result obtaining step
Include following steps:
Image acquisition step:Current image information is obtained, described image information includes at least one bar code image;
Image confirming step:Current image information is compared to obtain bar code region with bar code identification model.
3. the recognition methods of color bar code as claimed in claim 2, it is characterised in that also wrapped after image acquisition step
Include image preprocessing step:The current image information got is pre-processed, it is described pretreatment include remove noise with
Interference, image cutting and image normalization.
4. the recognition methods of color bar code as claimed in claim 2, it is characterised in that also wrapped after image confirming step
Include 3D aligning steps:3D corrections are carried out to bar code region to cause the bar code region to be adjusted to rectangle bar code region.
5. the recognition methods of the color bar code as described in Claims 2 or 3 or 4, it is characterised in that the bar code identification model
Process of establishing include following sub-step:
Model preprocessing step:The training bar code image got is pre-processed, it is described pretreatment include remove noise with
Interference, image cutting and image normalization;
Characteristic extraction step:Feature extraction is carried out to obtain bar code training set to pretreated training bar code image;
Model establishment step:Extraction standard template is to establish bar code identification model from bar code training set.
6. the recognition methods of color bar code as claimed in claim 5, it is characterised in that the training bar code image is colour
Bar code, black and white bar code or Quick Response Code.
7. the recognition methods of color bar code as claimed in claim 1, it is characterised in that also wrapped after result obtaining step
Include character check step:The character information is verified according to verification rule to confirm whether it is correct.
8. the recognition methods of color bar code as claimed in claim 7, it is characterised in that also wrapped after character check step
Include information forwarding step:Character information after verification is sent to display module and shown or by the character after verification
Information is sent to data processing module to be handled.
9. a kind of electronic equipment, including memory, processor and storage are on a memory and the meter that can run on a processor
Calculation machine program, it is characterised in that the coloured silk described in any one in claim 1-8 is realized during the computing device described program
The recognition methods of vitta shape code.
10. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that:The computer program
The method as described in claim 1-8 any one is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710996010.9A CN107862234A (en) | 2017-10-23 | 2017-10-23 | A kind of recognition methods of color bar code, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710996010.9A CN107862234A (en) | 2017-10-23 | 2017-10-23 | A kind of recognition methods of color bar code, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107862234A true CN107862234A (en) | 2018-03-30 |
Family
ID=61697633
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710996010.9A Pending CN107862234A (en) | 2017-10-23 | 2017-10-23 | A kind of recognition methods of color bar code, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107862234A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108921160A (en) * | 2018-05-04 | 2018-11-30 | 广东数相智能科技有限公司 | A kind of books recognition methods, electronic equipment and storage medium |
CN109255414A (en) * | 2018-07-06 | 2019-01-22 | 广东数相智能科技有限公司 | A kind of colour barcode made an inventory for books, books recognition methods, electronic equipment and storage medium |
CN109389000A (en) * | 2018-10-18 | 2019-02-26 | 龙马智芯(珠海横琴)科技有限公司 | A kind of barcode recognition method and the computer using this method |
CN109740440A (en) * | 2018-12-07 | 2019-05-10 | 深圳中广核工程设计有限公司 | A kind of archive management method and system based on Machine Vision Recognition |
CN109886009A (en) * | 2019-01-03 | 2019-06-14 | 广东智媒云图科技股份有限公司 | A kind of more equipment linkage unlocking methods, electronic equipment and storage medium |
CN111368576A (en) * | 2020-03-12 | 2020-07-03 | 成都信息工程大学 | Code128 bar Code automatic reading method based on global optimization |
CN111611822A (en) * | 2020-05-14 | 2020-09-01 | 科大讯飞股份有限公司 | Information storage method, device and system, electronic equipment and storage medium |
CN111797952A (en) * | 2020-06-09 | 2020-10-20 | 南岳生物制药有限公司 | Intelligent plasma quality interpretation instrument and quality detection method thereof |
CN112163800A (en) * | 2020-08-26 | 2021-01-01 | 北京易来特科技有限公司 | Management method and device of visual inspection tool |
CN112837008A (en) * | 2021-01-18 | 2021-05-25 | 上海燕汐软件信息科技有限公司 | Bar code reading method, device, equipment and storage medium |
CN113435450A (en) * | 2021-06-28 | 2021-09-24 | 澳柯玛股份有限公司 | Product number verification system and method based on OCR recognition |
CN114386552A (en) * | 2021-12-28 | 2022-04-22 | 阿依瓦(北京)技术有限公司 | Bar code generating method, bar code reading method, bar code generating device, bar code reading device and computer readable storage medium |
CN117057373A (en) * | 2022-11-29 | 2023-11-14 | 中知互联技术(深圳)有限公司 | Color code identification device and identification method |
CN112837008B (en) * | 2021-01-18 | 2024-06-04 | 山东浪潮创新创业科技有限公司 | Bar code reading method, device, equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH1139447A (en) * | 1997-07-18 | 1999-02-12 | Ootonikusu:Kk | Bar code and its reader |
CN101149813A (en) * | 2007-07-13 | 2008-03-26 | 中兴通讯股份有限公司 | Matrix type colorful two-dimensional bar code encoding and decoding method |
CN101251900A (en) * | 2008-03-11 | 2008-08-27 | 深圳信息职业技术学院 | Colourful commercial articles bar code and method for setting commercial articles information using the same |
CN106778441A (en) * | 2017-01-12 | 2017-05-31 | 西安科技大学 | A kind of graph image intelligent identifying system and its recognition methods |
-
2017
- 2017-10-23 CN CN201710996010.9A patent/CN107862234A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH1139447A (en) * | 1997-07-18 | 1999-02-12 | Ootonikusu:Kk | Bar code and its reader |
CN101149813A (en) * | 2007-07-13 | 2008-03-26 | 中兴通讯股份有限公司 | Matrix type colorful two-dimensional bar code encoding and decoding method |
CN101251900A (en) * | 2008-03-11 | 2008-08-27 | 深圳信息职业技术学院 | Colourful commercial articles bar code and method for setting commercial articles information using the same |
CN106778441A (en) * | 2017-01-12 | 2017-05-31 | 西安科技大学 | A kind of graph image intelligent identifying system and its recognition methods |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108921160A (en) * | 2018-05-04 | 2018-11-30 | 广东数相智能科技有限公司 | A kind of books recognition methods, electronic equipment and storage medium |
CN109255414A (en) * | 2018-07-06 | 2019-01-22 | 广东数相智能科技有限公司 | A kind of colour barcode made an inventory for books, books recognition methods, electronic equipment and storage medium |
CN109389000A (en) * | 2018-10-18 | 2019-02-26 | 龙马智芯(珠海横琴)科技有限公司 | A kind of barcode recognition method and the computer using this method |
CN109740440A (en) * | 2018-12-07 | 2019-05-10 | 深圳中广核工程设计有限公司 | A kind of archive management method and system based on Machine Vision Recognition |
CN109886009A (en) * | 2019-01-03 | 2019-06-14 | 广东智媒云图科技股份有限公司 | A kind of more equipment linkage unlocking methods, electronic equipment and storage medium |
CN111368576A (en) * | 2020-03-12 | 2020-07-03 | 成都信息工程大学 | Code128 bar Code automatic reading method based on global optimization |
CN111611822A (en) * | 2020-05-14 | 2020-09-01 | 科大讯飞股份有限公司 | Information storage method, device and system, electronic equipment and storage medium |
CN111797952B (en) * | 2020-06-09 | 2024-03-12 | 南岳生物制药有限公司 | Intelligent plasma quality judging and reading instrument and quality detection method thereof |
CN111797952A (en) * | 2020-06-09 | 2020-10-20 | 南岳生物制药有限公司 | Intelligent plasma quality interpretation instrument and quality detection method thereof |
CN112163800A (en) * | 2020-08-26 | 2021-01-01 | 北京易来特科技有限公司 | Management method and device of visual inspection tool |
CN112163800B (en) * | 2020-08-26 | 2023-11-14 | 北京易来特科技有限公司 | Management method and device for visual inspection tool |
CN112837008A (en) * | 2021-01-18 | 2021-05-25 | 上海燕汐软件信息科技有限公司 | Bar code reading method, device, equipment and storage medium |
CN112837008B (en) * | 2021-01-18 | 2024-06-04 | 山东浪潮创新创业科技有限公司 | Bar code reading method, device, equipment and storage medium |
CN113435450A (en) * | 2021-06-28 | 2021-09-24 | 澳柯玛股份有限公司 | Product number verification system and method based on OCR recognition |
CN114386552A (en) * | 2021-12-28 | 2022-04-22 | 阿依瓦(北京)技术有限公司 | Bar code generating method, bar code reading method, bar code generating device, bar code reading device and computer readable storage medium |
CN114386552B (en) * | 2021-12-28 | 2024-03-15 | 阿依瓦(北京)技术有限公司 | Bar code generating and reading method and device and computer readable storage medium |
CN117057373A (en) * | 2022-11-29 | 2023-11-14 | 中知互联技术(深圳)有限公司 | Color code identification device and identification method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107862234A (en) | A kind of recognition methods of color bar code, electronic equipment and storage medium | |
CN103914680B (en) | A kind of spray printing character picture identification and check system and method | |
CN102799850B (en) | A kind of barcode recognition method and device | |
US20190362193A1 (en) | Eyeglass positioning method, apparatus and storage medium | |
CN105957059B (en) | Electronic component missing part detection method and system | |
CN108520254B (en) | Text detection method and device based on formatted image and related equipment | |
CN110070536A (en) | A kind of pcb board component detection method based on deep learning | |
CN110728225B (en) | High-speed face searching method for attendance checking | |
CN108717543B (en) | Invoice identification method and device and computer storage medium | |
CN108960382B (en) | Color bar code and color calibration method thereof | |
CN112651289B (en) | Value-added tax common invoice intelligent recognition and verification system and method thereof | |
CN104268498A (en) | Two-dimension code recognition method and terminal | |
CN109740606B (en) | Image identification method and device | |
CN106156684B (en) | A kind of two-dimensional code identification method and device | |
CN110008909A (en) | A kind of real-time audit system of system of real name business based on AI | |
CN110490190B (en) | Structured image character recognition method and system | |
CN109583493A (en) | A kind of credit card detection and digit recognition method based on deep learning | |
CN109493384A (en) | Camera position and orientation estimation method, system, equipment and storage medium | |
CN109740609A (en) | A kind of gauge detection method and device | |
CN110647956A (en) | Invoice information extraction method combined with two-dimensional code recognition | |
CN108509870A (en) | A kind of Eriocheir sinensis uniqueness recognition methods based on images match | |
CN108875737A (en) | The method and system that whether detection check box is chosen in a kind of papery prescription document | |
CN114782770A (en) | License plate detection and recognition method and system based on deep learning | |
CN111091124A (en) | Spine character recognition method | |
CN100371945C (en) | Computer assisted calligraphic works distinguishing method between true and false |
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 |