CN104899879B - A kind of method of the online outward appearance detection of electric energy meter - Google Patents
A kind of method of the online outward appearance detection of electric energy meter Download PDFInfo
- Publication number
- CN104899879B CN104899879B CN201510262191.3A CN201510262191A CN104899879B CN 104899879 B CN104899879 B CN 104899879B CN 201510262191 A CN201510262191 A CN 201510262191A CN 104899879 B CN104899879 B CN 104899879B
- Authority
- CN
- China
- Prior art keywords
- electric energy
- energy meter
- outward appearance
- standard form
- value
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000003044 adaptive effect Effects 0.000 claims abstract description 17
- 239000004973 liquid crystal related substance Substances 0.000 claims abstract description 17
- 238000005286 illumination Methods 0.000 claims abstract description 5
- 230000018199 S phase Effects 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 230000000153 supplemental effect Effects 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 239000000428 dust Substances 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 239000000463 material Substances 0.000 abstract description 6
- 238000004364 calculation method Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Abstract
The invention discloses a kind of method of the online outward appearance detection of electric energy meter, this method, when carrying out outward appearance detection, by the self learning type ATL of foundation, can be overcome in detection process due to external condition suitable for extensive Intelligent electric energy meter automation detecting system(Illumination, koniology)Detection error is influenceed with the image intensity value difference caused by liquid crystal display process variations, False Rate is effectively reduced.The self learning type template matching algorithm based on adaptive threshold SSDA used can abandon the calculating to non-matching point quickly, match time is saved, matching efficiency is improved, and then improve the production efficiency of outward appearance detection, manpower and materials are saved, moreover it is possible to effective to solve the problem of False Rate is high.
Description
Technical field
The present invention relates to a kind of method of the online outward appearance detection of electric energy meter.
Background technology
Intelligent electric energy meter before installing and using must according to State Grid Corporation of China standard requirement its outward appearance is detected,
To ensure operation that intelligent electric energy meter is safe and reliable.In the prior art, intelligent electric energy meter shows number using LED liquid crystal displays technology
According to making data more directly perceived accurate, its data shown almost contains whole letters required for power consumer and power supply enterprise
Breath.But in the transport, storing process in intelligent electric energy meter, due to vibrations, wet environment and internal wiring loose contact etc.
Reason, causes the liquid crystal display of intelligent electric energy meter that screen fragmentation, blank screen, Hua Ping, display mess code, character short in size, signal lamp occurs
Not the problems such as not working.Therefore need to detect the outward appearance of intelligent electric energy meter before being taken into use, particularly its liquid crystal display is carried out
Detection.
Under artificial calibrating pattern, the outward appearance detection of electric energy meter is using the artificial method observed offline, i.e. staff takes
To after electric energy meter, observe by the naked eye display data and shell of liquid crystal display etc. and detected to carry out the outward appearance of electric energy meter.Such a side
Method needs substantial amounts of manpower and materials, wastes the substantial amounts of time, and production efficiency is low.In addition under automation line calibrating pattern, by
Cause image intensity value difference in the factor such as external condition (illumination, koniology) and liquid crystal display process variations, have a strong impact on inspection
Error is surveyed, causes electric energy meter False Rate higher.
The content of the invention
In view of the above-mentioned problems, the method that the present invention provides a kind of online outward appearance detection of electric energy meter, it is adaptable to extensive intelligence
The online outward appearance detection of automatic calibration of electric energy meter system, not only improves the production efficiency of outward appearance detection, uses manpower and material resources sparingly, also
It can effectively solve the problem that the problem of False Rate is high.
To realize above-mentioned technical purpose and the technique effect, the present invention is achieved through the following technical solutions:
A kind of method of the online outward appearance detection of electric energy meter, it is characterised in that comprise the following steps:
S01:The table bar code of the electric energy meter in automatic assembly line is scanned, and mould is judged according to the table bar code information scanned
It whether there is standard form in plate storehouse, if there is standard form, into step S02, otherwise into step S05;
S02:When at electric energy meter circulation to outward appearance detection module, image collecting device is clapped the liquid crystal display lighted
According to acquisition electric energy meter real-time online picture;
S03:The standard form of respective batch electric energy meter in ATL is called, starts the calculation based on adaptive threshold SSDA
Method, images match is carried out to real-time online picture and standard form;
S04:If the match is successful, the detection of electric energy meter outward appearance is qualified, conversely, then outward appearance detection is unqualified;
S05:Set up standard form:Choose several to have differences each other and qualified image, according to the spy of image
Levy data and set up the margin of tolerance, it is standard form that multiple images, which are integrated, into step S02.
It is preferred that, in step S05, the making step of standard form is specifically included:
05A) choose M liquid crystal display and there is process variations and the qualified electric energy meter of outward appearance, M >=1;
05B) when shooting liquid crystal display images, external condition is artificially changed according to actual calibrating environment, P is obtained and there is figure
As the qualified images of grey value difference, P >=M;
05C) qualified images subregion is pre-processed, the characteristic in each zonule is done to the projection on direction vector,
Maximum, the minimum value that respective cell domain is projected on direction vector in each image are extracted respectively, then are existed for each zonule
Direction vector sets up maximum curve, minimum value curve, and the margin of tolerance is set up according to this two curves;
It is standard form image by P image synthesises 05D) according to the margin of tolerance of foundation.
It is preferred that, start the algorithm based on adaptive threshold SSDA and image is carried out to real-time online picture and standard form
Match somebody with somebody, specifically include following steps:
03A) subregion is answered to pre-process realtime graphic S-phase;
Standard form T 03B) is called, by the image intensity value at realtime graphic S zonules midpoint and standard form TXiang Ying areas
Point in domain matches, and obtains matching point set through thick matching;
Smart matching 03C) is carried out in matching vertex neighborhood using adaptive threshold SSDA algorithms, smart matching result is preserved;
03D) the quantity N of record detection electric energy meter, if quantity is more than setting value L, into step 03E), otherwise enter step
Rapid 03F);
The qualified images for 03E) extracting a captured in real-time are added in ATL, N are reset, while according to supplemental image
Characteristic the margin of tolerance and standard form that have built up are adjusted, into step 03F);
03F) judge to detect whether to terminate, if not terminating, continue to gather realtime graphic and detected, while by N number
Value Jia 1.
This method is suitable for extensive Intelligent electric energy meter automation detecting system, when carrying out outward appearance detection, by building
Vertical self learning type ATL, can overcome in detection process due to external condition (illumination, koniology) and liquid crystal display technique
Image intensity value difference caused by difference influences on detection error, effectively reduces False Rate.Use based on adaptive threshold
SSDA self learning type template matching algorithm can abandon the calculating to non-matching point quickly, save match time, improve
Matching efficiency, and then the production efficiency of outward appearance detection is improved, save manpower and materials.
The beneficial effects of the invention are as follows:Suitable for the online outward appearance inspection of extensive Intelligent electric energy meter automation detecting system
Survey, not only improve the production efficiency of outward appearance detection, use manpower and material resources sparingly, moreover it is possible to be effective to solve the problem of False Rate is high.
Brief description of the drawings
Fig. 1 is the flow chart of the online outward appearance detection of electric energy meter of the present invention;
Fig. 2 is the self learning type template matching algorithm flow chart of the invention based on threshold adaptive SSDA;
Fig. 3 is the online outward appearance detection matching result figure of electric energy meter using the inventive method.
Embodiment
Technical solution of the present invention is described in further detail with specific embodiment below in conjunction with the accompanying drawings, so that ability
The technical staff in domain can be better understood from the present invention and can be practiced, but illustrated embodiment is not as the limit to the present invention
It is fixed.
A kind of method of the online outward appearance detection of electric energy meter, as described in Figure 1, comprises the following steps:
S01:The table bar code of the electric energy meter in automatic assembly line is scanned, and mould is judged according to the table bar code information scanned
It whether there is standard form in plate storehouse, if there is standard form, into step S02, otherwise into step S05;
S02:In automatic calibration line, when at electric energy meter circulation to outward appearance detection module, image collecting device is to
The liquid crystal display lighted is taken pictures, and obtains electric energy meter real-time online picture, wherein, preferred image harvester is industrial camera;
S03:The standard form of respective batch electric energy meter in ATL is called, starts the calculation based on adaptive threshold SSDA
Method, images match is carried out to real-time online picture and standard form;
S04:If the match is successful, the detection of electric energy meter outward appearance is qualified, conversely, then outward appearance detection is unqualified, electric energy meter need to be done
Recheck, return the processing such as factory;
S05:Set up standard form:Choose several to have differences each other and qualified image, according to the spy of image
Levy data and set up the margin of tolerance, it is standard form that multiple images, which are integrated, into step S02.
In view of manufacturer is different with batch, the content or font that the liquid crystal display of intelligent electric energy meter is shown can be different, therefore need
To make corresponding template according to information such as the mode of connection of intelligent electric energy meter, manufacturer and batches, and by the template made
It is stored in self learning type ATL, is called at any time when being detected so as to outward appearance, in the prior art, images match is carried out in ATL
Standard form only with single image template, and the present invention is then that to integrate multiple images template be standard form, and it makes
Step is specifically included:
05A) choose M liquid crystal display and there is process variations and the qualified electric energy meter of outward appearance, M >=1;
05B) when shooting liquid crystal display images, external condition is artificially changed according to actual calibrating environment, such as, changes illumination
Intensity, changes dust in air amount etc., obtains the P qualified images that there is image intensity value difference, P >=M;
05C) qualified images subregion is pre-processed, the characteristic in each zonule is done to the projection on direction vector,
Maximum, the minimum value that respective cell domain is projected on direction vector in each image are extracted respectively, then are existed for each zonule
Direction vector sets up maximum curve, minimum value curve, the margin of tolerance is set up according to this two curves, by image to be detected feature
Whether data fall in the margin of tolerance as the foundation for judging images match success or not;
It is standard form image by P image synthesises 05D) according to the margin of tolerance of foundation.
It is preferred that entering as shown in Fig. 2 starting the algorithm based on adaptive threshold SSDA to real-time online picture and standard form
Row images match, specifically includes following steps:
03A) during on-line checking, subregion is answered to pre-process realtime graphic S-phase;
Standard form T 03B) is called, by the image intensity value at realtime graphic S zonules midpoint and standard form TXiang Ying areas
Point in domain matches, and obtains matching point set through thick matching;
Smart matching 03C) is carried out in matching vertex neighborhood using adaptive threshold SSDA algorithms, smart matching result is preserved;
03D) the quantity N of record detection electric energy meter, if quantity is more than setting value L (such as L=100), into step
03E), otherwise into step 03F);
The qualified images for 03E) extracting a captured in real-time are added in ATL, N are reset, while according to supplemental image
Characteristic the margin of tolerance and standard form that have built up are adjusted, in real time adjustment ATL Plays Prototype drawing
Picture, into step 03F);
03F) judge to detect whether to terminate, if not terminating, continue to gather realtime graphic and detected, while by N number
Value Jia 1, due to continuously being detected with a batch of electric energy meter, so at the end of not detected with a batch of electric energy meter, directly
Tap into step 03A, start next circulation.
Self learning type template matching algorithm based on adaptive threshold SSDA mainly includes the foundation of self learning type ATL
With adaptive threshold SSDA template matches two parts, on the basis of the foundation of self learning type ATL, treated according to standard form
Detection image carries out respective partition domain, carries out thick matching.Again using the further essence matching of adaptive threshold SSDA algorithms, pass through meter
Operator figure and the error amount of template reach the purpose of search match point, and wherein add up error value E (i, j) calculation formula is:
S in formulai,j(m, n) is realtime graphic S pixel gray value, and T (m, n) is the pixel gray value of standard form,
(i, j) is the pixel chosen, and m × n is the zonule divided.
The key point of SSDA algorithms is that threshold value is chosen, and fixed threshold is not chosen in adaptive threshold SSDA algorithms of the present invention
Value, but using the margin of tolerance boundary value of standard form as initial threshold, the error accumulated value of each subgraph is calculated, if subsequent point
Accumulated value is more than or equal to threshold value, then threshold value keeps constant;If error accumulated value is less than threshold value, threshold value is set according to formula (2),
The like, complete images match related operation during constantly adjustment threshold value.
STI, j=K Δ ε+V (m, n) (2)
ST in formulai,jFor the threshold value of pixel (i, j), K is proportionality coefficient, and Δ ε is the front and rear pixel point tolerance selected twice
Difference, V (m, n) for standard form zonule m × n margins of tolerance boundary value.
Fig. 3 is the electric energy meter online outward appearance detection matching result figure using the inventive method, and traditional SSDA algorithms, automatically
The algorithm that change verification system was used originally is compared, and situation of the inventive algorithm in terms of matching efficiency, False Rate compares such as the institute of table 1
Show:
Several algorithm comparisons of table 1
Algorithm | Matching algorithm takes (s) | Electric energy meter False Rate (%) |
Traditional SSDA | 0.6 | 0.65 |
Automation line original uses algorithm | 0.45 | 0.63 |
Inventive algorithm | 0.05 | 0.07 |
The beneficial effects of the invention are as follows:Suitable for the online outward appearance inspection of extensive Intelligent electric energy meter automation detecting system
Survey, not only improve the production efficiency of outward appearance detection, use manpower and material resources sparingly, moreover it is possible to be effective to solve the problem of False Rate is high.
The preferred embodiments of the present invention are these are only, are not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure that bright specification and accompanying drawing content are made either equivalent flow conversion or to be directly or indirectly used in other related
Technical field, be included within the scope of the present invention.
Claims (6)
1. a kind of method of the online outward appearance detection of electric energy meter, it is characterised in that comprise the following steps:
S01:The table bar code of the electric energy meter in automatic assembly line is scanned, and according to the table bar code information judge templet storehouse scanned
In whether there is standard form, if there is standard form, into step S02, otherwise into step S05;
S02:When at electric energy meter circulation to outward appearance detection module, image collecting device is taken pictures to the liquid crystal display lighted,
Obtain electric energy meter real-time online picture;
S03:The standard form of respective batch electric energy meter in ATL is called, starts the algorithm based on adaptive threshold SSDA, it is right
Real-time online picture and standard form carry out images match, wherein:
Margin of tolerance boundary value in adaptive threshold SSDA algorithms using standard form calculates the error of each subgraph as initial threshold
Accumulated value, if the accumulated value of subsequent point is more than or equal to threshold value, threshold value keeps constant;If error accumulated value is less than threshold value, root
According to formula (2), threshold value is set, the like, complete images match related operation during constantly adjustment threshold value:
STI, j=K Δ ε+V (m, n) (2)
ST in formulai,jFor the threshold value of pixel (i, j), K is proportionality coefficient, the difference for the pixel point tolerance that Δ ε is selected twice for before and after
Value, V (m, n) is the boundary value of zonule m × n margins of tolerance of standard form;
S04:If the match is successful, the detection of electric energy meter outward appearance is qualified, conversely, then outward appearance detection is unqualified;
S05:Set up standard form:Choose several to have differences each other and qualified image, according to the characteristic of image
According to the margin of tolerance is set up, it is standard form that multiple images, which are integrated, into step S02.
2. the method for the online outward appearance detection of a kind of electric energy meter according to claim 1, it is characterised in that in step S05,
The making step of standard form is specifically included:
05A) choose M liquid crystal display and there is process variations and the qualified electric energy meter of outward appearance, M >=1;
05B) when shooting liquid crystal display images, external condition is artificially changed according to actual calibrating environment, P is obtained and there is image ash
The qualified images of angle value difference, P >=M;
05C) qualified images subregion is pre-processed, the characteristic in each zonule is done to the projection on direction vector, respectively
Extract respective cell the domain maximum, the minimum value that are projected on direction vector in each image, then be each zonule in vector
Maximum curve, minimum value curve are set up in direction, and the margin of tolerance is set up according to this two curves;
It is standard form image by P image synthesises 05D) according to the margin of tolerance of foundation.
3. the method for the online outward appearance detection of a kind of electric energy meter according to claim 1, it is characterised in that start based on adaptive
Answer threshold value SSDA algorithm to carry out images match to real-time online picture and standard form, specifically include following steps:
03A) subregion is answered to pre-process realtime graphic S-phase;
Standard form T 03B) is called, the image intensity value at realtime graphic S zonules midpoint and standard form T-phase are answered in region
Point match, obtain matching point set through thick matching;
Smart matching 03C) is carried out in matching vertex neighborhood using adaptive threshold SSDA algorithms, smart matching result is preserved;
03D) the quantity N of record detection electric energy meter, if quantity is more than setting value L, into step 03E), otherwise into step
03F);
The qualified images for 03E) extracting a captured in real-time are added in ATL, N are reset, while according to the spy of supplemental image
Levy data to be adjusted the margin of tolerance and standard form that have built up, into step 03F);
03F) judge to detect whether to terminate, if not terminating, continue collection realtime graphic and detected, while N numerical value is added
1。
4. a kind of method of the online outward appearance detection of electric energy meter according to claim 3, it is characterised in that L=100.
5. the method for the online outward appearance detection of a kind of electric energy meter according to claim 2, it is characterised in that according to actual calibrating
Environment artificially changes external condition, including changes intensity of illumination, changes dust in air amount.
6. a kind of method of the online outward appearance detection of electric energy meter according to claim 1-5 any one, it is characterised in that institute
It is industrial camera to state image collecting device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510262191.3A CN104899879B (en) | 2015-05-21 | 2015-05-21 | A kind of method of the online outward appearance detection of electric energy meter |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510262191.3A CN104899879B (en) | 2015-05-21 | 2015-05-21 | A kind of method of the online outward appearance detection of electric energy meter |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104899879A CN104899879A (en) | 2015-09-09 |
CN104899879B true CN104899879B (en) | 2017-11-03 |
Family
ID=54032524
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510262191.3A Active CN104899879B (en) | 2015-05-21 | 2015-05-21 | A kind of method of the online outward appearance detection of electric energy meter |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104899879B (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105424190A (en) * | 2015-09-30 | 2016-03-23 | 广州超音速自动化科技股份有限公司 | Grayscale detection method of product appearance |
CN106814066A (en) * | 2015-11-30 | 2017-06-09 | 富泰华工业(深圳)有限公司 | Appearance delection device and method |
CN108663373A (en) * | 2018-05-15 | 2018-10-16 | 国网重庆市电力公司电力科学研究院 | A kind of electric energy meter surface structure and component information acquisition comparison method and system |
CN109507198B (en) * | 2018-12-14 | 2021-12-07 | 航天科工智能机器人有限责任公司 | Mask detection system and method based on fast Fourier transform and linear Gaussian |
CN110082363A (en) * | 2019-05-31 | 2019-08-02 | 深圳元启智能技术有限公司 | The detection method and its device of ammeter appearance |
CN110082362A (en) * | 2019-05-31 | 2019-08-02 | 深圳元启智能技术有限公司 | The detection method and device of ammeter appearance |
CN116740385B (en) * | 2023-08-08 | 2023-10-13 | 深圳探谱特科技有限公司 | Equipment quality inspection method, device and system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3146232B2 (en) * | 1991-09-20 | 2001-03-12 | ヤマハ発動機株式会社 | Pattern matching method |
CN102298134A (en) * | 2010-06-23 | 2011-12-28 | 荣科科技股份有限公司 | Batch detection method and device for withdrawn electric energy meters |
CN103020586A (en) * | 2012-11-13 | 2013-04-03 | 浙江省电力公司电力科学研究院 | Method, device and system for identifying PCB (printed circuit board) |
CN103926554A (en) * | 2014-05-07 | 2014-07-16 | 国家电网公司 | Device and method for detecting visual identification consistency of intelligent ammeters |
CN104614701A (en) * | 2015-03-08 | 2015-05-13 | 无锡桑尼安科技有限公司 | Intelligent electric meter defect detection equipment |
-
2015
- 2015-05-21 CN CN201510262191.3A patent/CN104899879B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3146232B2 (en) * | 1991-09-20 | 2001-03-12 | ヤマハ発動機株式会社 | Pattern matching method |
CN102298134A (en) * | 2010-06-23 | 2011-12-28 | 荣科科技股份有限公司 | Batch detection method and device for withdrawn electric energy meters |
CN103020586A (en) * | 2012-11-13 | 2013-04-03 | 浙江省电力公司电力科学研究院 | Method, device and system for identifying PCB (printed circuit board) |
CN103926554A (en) * | 2014-05-07 | 2014-07-16 | 国家电网公司 | Device and method for detecting visual identification consistency of intelligent ammeters |
CN104614701A (en) * | 2015-03-08 | 2015-05-13 | 无锡桑尼安科技有限公司 | Intelligent electric meter defect detection equipment |
Non-Patent Citations (3)
Title |
---|
一种改进的模板匹配算法;罗中兵 等;《计算机应用》;20020328;第22卷(第3期);摘要、第3节 * |
一种新的自适应阈值SSDA算法;杜德生 等;《现代电子技术》;20100315;第0节、第2节 * |
基于计算机视觉的电能表检测系统;阮春雷 等;《计算机系统应用》;20130215;第22卷(第2期);第1.2节、第3节、第4.1节 * |
Also Published As
Publication number | Publication date |
---|---|
CN104899879A (en) | 2015-09-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104899879B (en) | A kind of method of the online outward appearance detection of electric energy meter | |
CN106228546B (en) | A kind of detection method and device of board | |
CN104537367B (en) | A kind of method of calibration of VIN codes | |
CN105306843B (en) | The bad point processing method and system of a kind of imaging sensor | |
CN106210471A (en) | A kind of outdoor face recognition method and system | |
CN105427320A (en) | Image segmentation and extraction method | |
CN109040745B (en) | Camera self-calibration method and device, electronic equipment and computer storage medium | |
CN105321191B (en) | Method and electronic apparatus for processing reflection in image | |
CN103913149B (en) | A kind of binocular range-measurement system and distance-finding method thereof based on STM32 single-chip microcomputer | |
CN109886918A (en) | Wire drawing burr detection method, electronic equipment and the storage medium of lithium battery pole slice | |
CN102436578B (en) | Formation method for dog face characteristic detector as well as dog face detection method and device | |
CN105095181A (en) | Spam comment detection method and device | |
CN105184771A (en) | Adaptive moving target detection system and detection method | |
CN107333123A (en) | Detecting system of focusing and focusing detection method | |
CN104512579A (en) | Defect detecting method for bracing wire on transparent packing material | |
WO2023280080A1 (en) | Shadow elimination device and method, empty disk recognition device and method | |
CN106530315B (en) | Target extraction system and method for medium and small objects under full angle | |
CN114612418A (en) | Method, device and system for detecting surface defects of mouse shell and electronic equipment | |
CN102799861A (en) | Method for rapidly identifying reading of instrument by using color | |
CN104159102B (en) | Grey menu detection method and checkout gear | |
CN106959301B (en) | Nonwoven fabric stain detection system and nonwoven fabric stain detection method | |
CN104050676A (en) | Backlighting image detection method and device based on Logistic regression model | |
CN103091332B (en) | Detection method and detection system of U-shaped powder pipe based on machine vision | |
CN208476813U (en) | Industrial part defect detecting device | |
CN106767566A (en) | A kind of workpiece quality monitors appraisal procedure and monitoring system on-line |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |