CN110502990A - The method and system of data acquisition are carried out using image procossing - Google Patents
The method and system of data acquisition are carried out using image procossing Download PDFInfo
- Publication number
- CN110502990A CN110502990A CN201910645911.2A CN201910645911A CN110502990A CN 110502990 A CN110502990 A CN 110502990A CN 201910645911 A CN201910645911 A CN 201910645911A CN 110502990 A CN110502990 A CN 110502990A
- Authority
- CN
- China
- Prior art keywords
- character
- frame
- identification
- font
- module
- 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
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000000605 extraction Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0423—Input/output
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/4183—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by data acquisition, e.g. workpiece identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- 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
- G06V30/148—Segmentation of character regions
- G06V30/158—Segmentation of character regions using character size, text spacings or pitch estimation
-
- 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
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Manufacturing & Machinery (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention discloses a kind of method and system that data acquisition is carried out using image procossing, comprising: S1, the identification frame that the corresponding numerical value of each parameter that continues is calibrated in the image of acquisition；S2, matrixing processing and contrast Edge contrast are carried out to identification frame with the character in prominent identification frame；S3, the character zone identified in frame is identified, cutting is carried out to obtain block character to character zone according to the space of intercharacter, to each character in each piece of character, is compared by the shape in the shape and correspondence database of character and each character is gone out with match cognization；S4, recognition result is stored in the database of edge calculations gateway.The present invention passes through the screenshotss to control system HMI, image procossing is carried out to screenshot picture, identify the data such as text, number and the character in picture, recognition result parsing output is stored in the database of edge calculations gateway, the present invention can quickly and accurately identify each output parameter in screenshot picture, and overall cost is lower.
Description
Technical field
The present invention relates to data acquisition technology fields, more particularly to a kind of side for carrying out data acquisition using image procossing
Method and system.
Background technique
In industry internet field, various industrial equipments are faced, especially more old control equipment, in full
Cutting machine, numerical control bender etc. are controlled, the data of device controller can not be obtained by the communications protocol of standard.Industrial field control
System is often based upon the operating system platforms such as Windows and Linux, and part system is based on Embedded dedicated control system, right
In the interface HMI of control system, the generally relevant parameter of meeting real-time display equipment, such as coordinate value, warning information content, often
These data are that have the data of important value to industry internet, need to carry out data acquisition.
Summary of the invention
The present invention is in view of the problems of the existing technology and insufficient, provides and a kind of carries out data acquisition using image procossing
Method and system.
The present invention is to solve above-mentioned technical problem by following technical proposals:
The present invention provides a kind of method for carrying out data acquisition using image procossing, it is characterized in that comprising following step
It is rapid:
S1, the identification frame that the corresponding numerical value of each parameter that continues is calibrated in the image of acquisition；
S2, matrixing processing and contrast Edge contrast are carried out to identification frame with the character in prominent identification frame；
S3, it identifies the character zone identified in frame, cutting is carried out to character zone to obtain according to the space of intercharacter
Block character, to each character in each piece of character, by the shape in the shape and correspondence database of character compare with
Match cognization goes out each character；
S4, recognition result parsing output is stored in the database of edge calculations gateway.
Preferably, in step sl, upper side frame, lower frame, left frame or the left frame of fine tuning identification frame, so that identification
The background interference that undopes in frame element.
Preferably, in step s3, cover font for the part in block character, by cover the shape of font with it is corresponding
Shape in database is compared to be gone out to cover character represented by font with match cognization.
Preferably, collecting the example picture for covering font, identification frame contents extraction is carried out to font is covered in example picture,
Background denoising and contrast Edge contrast are taken, text is covered to treated by jTessBoxEditor tool and is marked again
Note, counterweight labeled data carry out retraining, generate new text library, cover font to following part with new text library and carry out
Identification prediction.
The present invention also provides a kind of systems for carrying out data acquisition using image procossing, it is characterized in that comprising calibration
Module, processing module, identification module and memory module；
The demarcating module is used to calibrate the identification frame of the corresponding numerical value of each parameter that continues in the image of acquisition；
The processing module is used to carry out identification frame matrixing processing and contrast Edge contrast in prominent identification frame
Character；
The identification module for identification go out identification frame in character zone, according to the space of intercharacter to character zone into
Row cutting, to each character in each piece of character, passes through the shape in the shape and correspondence database of character to obtain block character
Shape, which is compared, goes out each character with match cognization；
The memory module is used to for recognition result parsing output being stored in the database of edge calculations gateway.
Preferably, the demarcating module is used to finely tune upper side frame, lower frame, left frame or the left frame of identification frame, so that
The background interference element that undopes must be identified in frame.
Preferably, covering font for the part in block character, the identification module is used for the shape by covering font
It compares to go out to cover character represented by font with match cognization with the shape in correspondence database.
Preferably, the sample acquisition module, which is used to collect, covers font the system also includes sample acquisition module
Example picture carries out identification frame contents extraction to font is covered in example picture, takes background denoising and contrast Edge contrast,
It covers text to treated by jTessBoxEditor tool to be marked again, counterweight labeled data carries out retraining, raw
The text library of Cheng Xin covers font to following part with new text library and carries out identification prediction.
On the basis of common knowledge of the art, above-mentioned each optimum condition, can any combination to get each preferable reality of the present invention
Example.
The positive effect of the present invention is that:
The present invention carries out image procossing by the screenshotss to control system HMI, and to the picture of screenshotss, identifies in picture
Recognition result parsing output is stored in the database of edge calculations gateway, energy of the present invention by the data such as text, number and character
Enough each output parameters quickly and accurately identified in screenshot picture, overall cost are lower.
Detailed description of the invention
Fig. 1 is the flow chart of the method that data acquisition is carried out using image procossing of present pre-ferred embodiments.
Fig. 2 is that the schematic diagram of position is confined in the Image Processing parameter identification of present pre-ferred embodiments.
Fig. 3 is the structural block diagram of the system that data acquisition is carried out using image procossing of present pre-ferred embodiments.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
As shown in Figure 1, the present embodiment provides a kind of methods for carrying out data acquisition using image procossing comprising following step
It is rapid:
Step 101, the identification frame that the corresponding numerical value of each parameter that continues is calibrated in the image of acquisition, fine tuning identification frame
Upper side frame, lower frame, left frame or left frame see Fig. 2 so that undoping background interference element in identification frame.
To each parameter request up and down four location of pixels as far as possible other background interference elements of undoping (such as
The jamming pattern of frame, horizontal line etc) on the basis of all include by content of parameter as much as possible to identification frame (bounding
Box in), the referred to as benchmark (base line) of Coordinate Adjusting.
Step 102 carries out matrixing processing and contrast Edge contrast to identification frame with the character in prominent identification frame.
The processing of background noise first has to the bounding box for correctly intercepting out content of parameter.Guarantee its bounding
Few as far as possible in box includes various background noises.Such as frame, interfering line etc..It the case where also avoiding double backgrounds simultaneously, goes
The method made an uproar is to carry out matrixing processing by the pixel of the content of parameter to interception.The distribution rule of pixel are looked on this basis
Rule, is then sharpened processing to chromatic value.
Step 103, identify identification frame in character zone, according to the space of intercharacter to character zone carry out cutting with
Block character is obtained, to each character in each piece of character, is carried out pair by the shape in the shape and correspondence database of character
Than going out each character with match cognization.
Wherein, font is covered for the part in block character, the shape in shape and correspondence database by covering font
Shape is compared to be gone out to cover character represented by font with match cognization.
The example picture for covering font is collected, identification frame contents extraction is carried out to font is covered in example picture, takes back
Scape denoising and contrast Edge contrast are covered text to treated by jTessBoxEditor tool and are marked again, right
Weight labeled data carries out retraining, generates new text library, covers font to following part with new text library and identifies
Prediction.
Recognition result parsing output is stored in the database of edge calculations gateway by step 104.
As shown in figure 3, the present embodiment also provides a kind of system for carrying out data acquisition using image procossing comprising calibration
Module 1, processing module 2, identification module 3 and memory module 4.
The demarcating module 1 is used to calibrate the identification frame of the corresponding numerical value of each parameter that continues in the image of acquisition,
Upper side frame, lower frame, left frame or the left frame of fine tuning identification frame, so that the background interference element that undopes in identification frame.
The processing module 2 is used to carry out identification frame matrixing processing and contrast Edge contrast in prominent identification frame
Character.
The identification module 3 goes out the character zone in identification frame for identification, according to the space of intercharacter to character zone
Cutting is carried out to obtain block character, to each character in each piece of character, by the shape and correspondence database of character
Shape, which is compared, goes out each character with match cognization.
Wherein, in block character part cover font, the identification module be used for by cover font shape with
Shape in correspondence database is compared to be gone out to cover character represented by font with match cognization.
The system also includes sample acquisition module, the sample acquisition module is used to collect the example figure for covering font
Piece carries out identification frame contents extraction to font is covered in example picture, takes background denoising and contrast Edge contrast, by
JTessBoxEditor tool is covered text to treated and is marked again, and counterweight labeled data carries out retraining, generates new
Text library, font is covered to following part with new text library and carries out identification prediction.
The memory module 4 is used to for recognition result parsing output being stored in the database of edge calculations gateway.
For the old equipment of industry spot, the communications protocol of standard is not often supported, conventional data acquisition thinking is very
Hardly possible, which is realized, acquires the data of the type equipment, and this programme can make up the deficiency of conventional data acquisition scheme, can be quick
Accurately identify each output parameter in screenshot picture, overall cost is lower.
Although specific embodiments of the present invention have been described above, it will be appreciated by those of skill in the art that these
It is merely illustrative of, protection scope of the present invention is defined by the appended claims.Those skilled in the art is not carrying on the back
Under the premise of from the principle and substance of the present invention, many changes and modifications may be made, but these are changed
Protection scope of the present invention is each fallen with modification.
Claims (8)
1. it is a kind of using image procossing carry out data acquisition method, which is characterized in that itself the following steps are included:
S1, the identification frame that the corresponding numerical value of each parameter that continues is calibrated in the image of acquisition；
S2, matrixing processing and contrast Edge contrast are carried out to identification frame with the character in prominent identification frame；
S3, it identifies the character zone identified in frame, cutting is carried out to character zone to obtain block word according to the space of intercharacter
Symbol, to each character in each piece of character, is compared by the shape of character with the shape in correspondence database to match
Identify each character；
S4, recognition result parsing output is stored in the database of edge calculations gateway.
2. the method as described in claim 1 for carrying out data acquisition using image procossing, which is characterized in that in step sl,
Upper side frame, lower frame, left frame or the left frame of fine tuning identification frame, so that the background interference element that undopes in identification frame.
3. the method as described in claim 1 for carrying out data acquisition using image procossing, which is characterized in that in step s3,
For in block character part cover font, by cover font shape and correspondence database in shape compare with
Character represented by font is covered with identifying.
4. the method as claimed in claim 3 for carrying out data acquisition using image procossing, which is characterized in that collect and cover font
Example picture, in example picture cover font carry out identification frame contents extraction, take at background denoising and contrast sharpening
Reason is covered text to treated by jTessBoxEditor tool and is marked again, and counterweight labeled data carries out retraining,
New text library is generated, font is covered to following part with new text library and carries out identification prediction.
5. it is a kind of using image procossing carry out data acquisition system, which is characterized in that it include demarcating module, processing module,
Identification module and memory module；
The demarcating module is used to calibrate the identification frame of the corresponding numerical value of each parameter that continues in the image of acquisition；
The processing module is used to carry out identification frame matrixing processing and contrast Edge contrast with the word in prominent identification frame
Symbol；
The identification module goes out the character zone in identification frame for identification, is cut according to the space of intercharacter to character zone
Point to obtain block character, to each character in each piece of character, by the shape in the shape and correspondence database of character into
Row comparison goes out each character with match cognization；
The memory module is used to for recognition result parsing output being stored in the database of edge calculations gateway.
6. the system as claimed in claim 5 for carrying out data acquisition using image procossing, which is characterized in that the demarcating module
For finely tuning upper side frame, lower frame, left frame or the left frame of identification frame, so that the background interference member that undopes in identification frame
Element.
7. the system as claimed in claim 5 for carrying out data acquisition using image procossing, which is characterized in that in block character
Part cover font, the identification module be used for by cover font shape and correspondence database in shape compare
Go out to cover character represented by font with match cognization.
8. the system as claimed in claim 7 for carrying out data acquisition using image procossing, which is characterized in that the system is also wrapped
Include sample acquisition module, the sample acquisition module is used to collect the example picture of cover font, to covering word in example picture
Body carries out identification frame contents extraction, background denoising and contrast Edge contrast is taken, by jTessBoxEditor tool to place
Cover text after reason is marked again, and counterweight labeled data carries out retraining, new text library is generated, with new text library pair
It covers font and carries out identification prediction in following part.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910645911.2A CN110502990B (en) | 2019-07-17 | 2019-07-17 | Method and system for data acquisition by image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910645911.2A CN110502990B (en) | 2019-07-17 | 2019-07-17 | Method and system for data acquisition by image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110502990A true CN110502990A (en) | 2019-11-26 |
| CN110502990B CN110502990B (en) | 2022-06-03 |
Family
ID=68585332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910645911.2A Active CN110502990B (en) | 2019-07-17 | 2019-07-17 | Method and system for data acquisition by image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110502990B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111125217A (en) * | 2019-12-13 | 2020-05-08 | 天津润华科技有限公司 | Editable visual image recognition type intelligent data acquisition system and application thereof |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102446266A (en) * | 2010-09-30 | 2012-05-09 | 北京中远通科技有限公司 | Device, system and method for automatically identifying industrial number |
| CN103150293A (en) * | 2011-12-06 | 2013-06-12 | 富泰华工业（深圳）有限公司 | Electronic device with messy code recovery function and messy code recovery method |
| CN103679147A (en) * | 2013-12-05 | 2014-03-26 | 广州绿怡信息科技有限公司 | Method and device for identifying model of mobile phone |
| CN104408931A (en) * | 2014-10-29 | 2015-03-11 | 合肥指南针电子科技有限责任公司 | Incomplete sign license plate identification system and method |
| CN104636748A (en) * | 2013-11-14 | 2015-05-20 | 张伟伟 | License plate recognition method and device |
| CN104951784A (en) * | 2015-06-03 | 2015-09-30 | 杨英仓 | Method of detecting absence and coverage of license plate in real time |
| CN105528137A (en) * | 2015-11-27 | 2016-04-27 | 努比亚技术有限公司 | Method and apparatus for self-adaptive screen shot according to occluded area |
| CN106682667A (en) * | 2016-12-29 | 2017-05-17 | 成都数联铭品科技有限公司 | Image-text OCR (optical character recognition) system for uncommon fonts |
| CN107292205A (en) * | 2016-03-31 | 2017-10-24 | 阿里巴巴集团控股有限公司 | A kind of input method and device, electronic equipment |
| CN207250056U (en) * | 2017-07-31 | 2018-04-17 | 比亚迪股份有限公司 | A kind of backlight type matrix group |
| CN109389121A (en) * | 2018-10-30 | 2019-02-26 | 金现代信息产业股份有限公司 | A kind of nameplate recognition methods and system based on deep learning |
| CN109858327A (en) * | 2018-12-13 | 2019-06-07 | 安徽清新互联信息科技有限公司 | A kind of character segmentation method based on deep learning |
-
2019
- 2019-07-17 CN CN201910645911.2A patent/CN110502990B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102446266A (en) * | 2010-09-30 | 2012-05-09 | 北京中远通科技有限公司 | Device, system and method for automatically identifying industrial number |
| CN103150293A (en) * | 2011-12-06 | 2013-06-12 | 富泰华工业（深圳）有限公司 | Electronic device with messy code recovery function and messy code recovery method |
| CN104636748A (en) * | 2013-11-14 | 2015-05-20 | 张伟伟 | License plate recognition method and device |
| CN103679147A (en) * | 2013-12-05 | 2014-03-26 | 广州绿怡信息科技有限公司 | Method and device for identifying model of mobile phone |
| CN104408931A (en) * | 2014-10-29 | 2015-03-11 | 合肥指南针电子科技有限责任公司 | Incomplete sign license plate identification system and method |
| CN104951784A (en) * | 2015-06-03 | 2015-09-30 | 杨英仓 | Method of detecting absence and coverage of license plate in real time |
| CN105528137A (en) * | 2015-11-27 | 2016-04-27 | 努比亚技术有限公司 | Method and apparatus for self-adaptive screen shot according to occluded area |
| CN107292205A (en) * | 2016-03-31 | 2017-10-24 | 阿里巴巴集团控股有限公司 | A kind of input method and device, electronic equipment |
| CN106682667A (en) * | 2016-12-29 | 2017-05-17 | 成都数联铭品科技有限公司 | Image-text OCR (optical character recognition) system for uncommon fonts |
| CN207250056U (en) * | 2017-07-31 | 2018-04-17 | 比亚迪股份有限公司 | A kind of backlight type matrix group |
| CN109389121A (en) * | 2018-10-30 | 2019-02-26 | 金现代信息产业股份有限公司 | A kind of nameplate recognition methods and system based on deep learning |
| CN109858327A (en) * | 2018-12-13 | 2019-06-07 | 安徽清新互联信息科技有限公司 | A kind of character segmentation method based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 胡晓霞 等: "基于可变形模板匹配的变形字体识别", 《电子设计工程》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111125217A (en) * | 2019-12-13 | 2020-05-08 | 天津润华科技有限公司 | Editable visual image recognition type intelligent data acquisition system and application thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110502990B (en) | 2022-06-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110059694B (en) | Intelligent identification method for character data in complex scene of power industry | |
| CN106683075B (en) | Method for detecting bolt defects at cross arm of power transmission line tower | |
| CN110942074A (en) | Character segmentation recognition method and device, electronic equipment and storage medium | |
| DE112020005377B4 (en) | SYSTEMS AND METHODS FOR AUTOMATIC CAMERA INSTALLATION GUIDANCE | |
| CN109726661B (en) | Image processing method and apparatus, medium, and computing device | |
| CN102750555B (en) | Expression identification device applied to instant messaging tool | |
| CN109934221B (en) | Attention mechanism-based automatic analysis, identification and monitoring method and system for power equipment | |
| CN110119742B (en) | Container number identification method and device and mobile terminal | |
| US20150262030A1 (en) | Image processing device, image processing method, and image processing program | |
| CN111461100A (en) | Bill identification method and device, electronic equipment and storage medium | |
| US20220301281A1 (en) | System and method for identifying fractures in digitized x-rays | |
| CN113238578A (en) | Routing planning method and system for power tower unmanned aerial vehicle inspection route | |
| CN107273890A (en) | Graphical verification code recognition methods and device for character combination | |
| CN112381765A (en) | Equipment detection method, device, equipment and storage medium based on artificial intelligence | |
| CN106940804A (en) | Architectural engineering material management system form data method for automatically inputting | |
| CN110502990A (en) | The method and system of data acquisition are carried out using image procossing | |
| CN115661160A (en) | Panel defect detection method, system, device and medium | |
| CN116434252A (en) | Training of image recognition model and image recognition method, device, medium and equipment | |
| CN112446884B (en) | Positioning method and device for power transmission line in laser point cloud and terminal equipment | |
| CN118230405A (en) | Method and device for identifying tool holding behavior | |
| KR102366396B1 (en) | RGB-D Data and Deep Learning Based 3D Instance Segmentation Method and System | |
| CN116245838A (en) | Monitoring method, monitoring device, equipment and medium for rock-soil exploration behaviors | |
| CN112581472B (en) | Target surface defect detection method facing human-computer interaction | |
| CN115326832A (en) | Automatic detection method and automatic detection device for wafer package | |
| CN110083807B (en) | Contract modification influence automatic prediction method, device, medium and electronic equipment |
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 |