CN106996934A - Polyphaser vision detection system and detection method - Google Patents
Polyphaser vision detection system and detection method Download PDFInfo
- Publication number
- CN106996934A CN106996934A CN201610048485.0A CN201610048485A CN106996934A CN 106996934 A CN106996934 A CN 106996934A CN 201610048485 A CN201610048485 A CN 201610048485A CN 106996934 A CN106996934 A CN 106996934A
- Authority
- CN
- China
- Prior art keywords
- key point
- image
- detected
- respective image
- processing unit
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 55
- 230000002950 deficient Effects 0.000 claims abstract description 18
- 238000000034 method Methods 0.000 claims description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004148 unit process 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of polyphaser vision detection system and detection method, and the detecting system includes multiple micro-cameras and graphics processing unit.Multiple micro-cameras are arranged on the top of object to be detected, and multiple micro-cameras obtain multiple images of object to be detected by way of auto-focusing.Graphics processing unit is electrically connected with multiple micro-cameras, and multiple images got are matched with default respective image template respectively；When all images are with default respective image template matches, the object to be detected is judged for certified products, otherwise, judges the object to be detected for defective work.
Description
Technical field
The present invention relates to Product checking field, and more particularly to a kind of polyphaser vision detection system and detection side
Method.
Background technology
With the continuous progress of computer technology, the detection of industrial products is via traditional manually detection
Gradually be converted to the automatic detection of automation equipment.Automatic detection not only considerably reduce manually detect into
This, while also improving the detection efficiency of product to a certain extent.
Existing automatic testing method is that the single CCD camera on automatic equipment obtains object to be detected
Image, the image of acquisition and standard picture are compared, and certified products are then considered when both are identical, no
Then, it is defective work.Because single CCD camera can only clearly capture a certain plane of object to be detected
Image, and (current most industrial products are this for the object to be detected with multiple high low degrees
Plant product), existing mode is to complete multiple height by repeatedly adjusting the focal length of single CCD camera to put down
The image in face is obtained.The problem of there is slow acquisition speed, high cost and big cost in this acquisition modes, also just
It is the High Precision Automatic detection that these problems hinder existing industrial products.
The content of the invention
The present invention is in order to overcome single CCD camera in the prior art to obtaining the quilt with multiple high low degrees
Detection object image exist the problem of acquisition speed is slow, cost is high there is provided one kind can quick obtaining have it is multiple
The polyphaser vision detection system and detection method of the object to be detected image of high low degree.
To achieve these goals, the present invention provides a kind of polyphaser vision detection system, including multiple miniature
Camera and graphics processing unit.Multiple micro-cameras are arranged on around object to be detected, multiple micro-cameras
Multiple images of object to be detected are obtained by way of auto-focusing.Graphics processing unit is electrically connected with multiple
Micro-camera, multiple images got are matched with default respective image template respectively；When all
When image is with default respective image template matches, judge that the object to be detected, for certified products, otherwise, is sentenced
The object to be detected break for defective work.
In one embodiment of the invention, polyphaser vision detection system also includes industrial computer and display, industry control
Machine is connected with graphics processing unit, receives the result of graphics processing unit and is shown over the display
Show.
In one embodiment of the invention, polyphaser vision detection system also includes the discharge being connected with industrial computer
Unit, industrial computer receives the defective work signal of graphics processing unit output and extremely discharges the signal output
Unit, deliverying unit rejects defective work from flowing water Working position.
In one embodiment of the invention, polyphaser vision detection system also includes memory module, memory module electricity
Property connection graphics processing unit, image and data after storage image processing unit processes.
Corresponding, the present invention provides a kind of polyphaser visible detection method, including：
Multiple micro-cameras obtain multiple images of object to be detected by way of auto-focusing；
Multiple images got are matched with default respective image template respectively；When all images are equal
During with default respective image template matches, the object to be detected is judged for certified products, otherwise, judges the quilt
Detection object is defective work.
In one embodiment of the invention, multiple images got are entered with default respective image template respectively
The step of row matching, includes：
For the every image got, the key point of the image is extracted；
Feature description is carried out to key point；
In the key point and default respective image template that image is obtained according to the feature profile matching of key point
Key point, when all key points in all key points and default respective image template for obtaining image are complete
During matching, it is believed that the image got and default respective image template matches.
In one embodiment of the invention, the key point of the every image got using the extraction of SIFT algorithms is simultaneously right
Key point carries out feature description, and specific step is as follows：
The metric space of image is set up, the key point of image is searched in metric space, key point place is obtained
The position of pixel；
Gradient amplitude size m (x, y) and the gradient side of key point position are obtained by four neighborhoods of key point
It is that key point assigns 128 dimension parameters by amplitude size m (x, y) and gradient direction θ (x, y) to θ (x, y),
So that each key point has position, residing yardstick and three, direction information, so that it is determined that a SIFT feature
Region.
In one embodiment of the invention, using the Euclidean distance of key point characteristic vector come the pass to extracting image
The matching of key point and the key point in default respective image template.
In one embodiment of the invention, polyphaser visible detection method also includes：By multiple images got
Carry out passing through multiple figures after whether matching judgment object to be detected is qualified with default respective image template respectively
As obtaining the parameter of object to be detected and being stored.
In summary, the polyphaser vision detection system that provides of the present invention and detection method compared with prior art,
With advantages below：
By setting multiple micro-cameras, compared with existing single CCD camera, due to each Miniature phase
Machine can all realize auto-focusing, in IMAQ without carrying out the multiple focal length for adjusting micro-camera again
The disposable IMAQ to the object to be detected with different high low degrees is realized, the setting is substantially increased
The speed of IMAQ, reduces the process of IMAQ, so as to reach the purpose of reduction testing cost.It is logical
Cross setting graphics processing unit to handle the picture that multiple micro-cameras are obtained, by judging to get
Multiple images whether match to realize the quilt with different high low degrees from default respective image template respectively
Detect the qualified detection of article.
By setting the result after industrial computer and display, graphics processing unit to be shown by display,
It is easy to operator to observe.By setting the deliverying unit that is connected with industrial computer, deliverying unit is by defective work
Directly rejected from flowing water Working position, realize automatically screening.
It is cited below particularly preferable for above and other objects of the present invention, feature and advantage can be become apparent
Embodiment, and coordinate accompanying drawing, it is described in detail below.
Brief description of the drawings
Fig. 1 show the structural representation of the polyphaser vision detection system of one embodiment of the invention offer.
Fig. 2 show the flow chart of the polyphaser visible detection method of one embodiment of the invention offer.
Fig. 3 show in Fig. 2 by multiple images got respectively with default respective image template carry out
The flow chart matched somebody with somebody.
Embodiment
As shown in figure 1, the polyphaser vision detection system that the present embodiment is provided includes multiple Hes of micro-camera 1
Graphics processing unit 2.Multiple micro-cameras 1 are arranged on around object to be detected 100, multiple micro-cameras
1 obtains multiple images of object to be detected 100 by way of auto-focusing.Graphics processing unit 2 electrically connects
Multiple micro-cameras 1 are connect, multiple images got are matched with default respective image template respectively；
When all images are with default respective image template matches, the object to be detected is judged for certified products, it is no
Then, judge the object to be detected for defective work.
The polyphaser vision detection system that the present embodiment is provided is by setting multiple micro-cameras 1, each Miniature phase
Machine is respectively provided with the function of auto-focusing.When object to be detected has the plane of multiple different heights, Duo Gewei
Type camera 1 can respectively to multiple different heights flat focus, collection different height plane at picture rich in detail
And export multiple pictures rich in detail to graphics processing unit 2.Graphics processing unit 2 by multiple images of acquisition and
Default respective image template is matched, so as to judge whether the object to be detected is certified products.This implementation
The polyphaser vision detection system that example is provided can realize the inspection of the testee with different height plane, with
Traditional check system is compared, the process for not only greatly reducing detection, while detection is also greatly improved
Efficiency, reduces the cost of detection.
Further to improve the speed of data processing, in the present embodiment, each micro-camera 1 is correspondingly arranged
There is a graphics processing unit 2, each graphics processing unit 2 is individually matched to the image of acquisition, had
Very high processing speed.However, the present invention is not limited in any way to this.In other embodiments, it can be set
Multiple micro-cameras 1 share a graphics processing unit 2.
In the present embodiment, polyphaser vision detection system also includes industrial computer 3 and display 4, industrial computer 3
It is connected with graphics processing unit 2, the result of reception graphics processing unit 2 is simultaneously enterprising in display 4
Row display.In the present embodiment, polyphaser vision detection system also includes the discharge being connected with industrial computer 3
Unit 5, industrial computer 3 receive graphics processing unit 2 output defective work signal and by the signal output extremely
Deliverying unit 5, deliverying unit 5 rejects defective work from flowing water Working position, realizes the inspection of defective work
Survey and screen.
In the present embodiment, polyphaser vision detection system also includes memory module 6, and memory module 6 electrically connects
Graphics processing unit 2 is connect, image and data after the processing of storage image processing unit 2.Specifically, figure is worked as
As processing unit 2 obtains the parameter of testee, the Different Plane of such as testee by the image got
The data such as height.
Corresponding with polyphaser vision detection system, the present invention also provides a kind of polyphaser visible detection method,
Including：
Step S10, multiple micro-cameras obtain multiple images of object to be detected by the way of auto-focusing.
The present invention is not construed as limiting to specific auto-focusing mode, and the mode of auto-focusing can be with existing mobile phone camera
Focusing mode it is identical.
Step S20, multiple images got are matched with default respective image template respectively；Work as institute
When having image with default respective image template matches, the object to be detected is judged for certified products, otherwise,
Judge the object to be detected for defective work.
Step S30, the parameter by multiple images acquisition object to be detected are simultaneously stored.In the present embodiment,
Graphics processing unit 2 obtains the parameter of object to be detected, such as Different Plane by multiple images got
The data such as height.Specifically, the position on image where Different Plane can be obtained by following algorithm
Coordinate, so as to obtain the height of Different Plane.
In the present embodiment, multiple images got are matched with default respective image template respectively
The step of include：
Step S21, every image for getting, extract the key point of the image；
Step S22, to key point carry out feature description；
Step S23, key point and default respective image according to the feature profile matching of key point acquisition image
Key point in template, it is relevant with the institute in default respective image template when obtaining all key points of image
When key point is matched completely, it is believed that the image got and default respective image template matches.
In the present embodiment, in the step s 21, the pass of the every image got is extracted using SIFT algorithms
Key point simultaneously carries out feature description to key point.However, the present invention is not limited in any way to this.Implement in other
Can be using other image matching methods come the image to acquisition and the progress of default respective image template in example
Match somebody with somebody.
The specific matching step of SIFT algorithms is as follows：
First, the metric space of image is set up, the key point of image is searched in metric space, key is obtained
The position of pixel where point.Specifically, image is all converted into gray-scale map first.Then, use with
Lower formula is handled：
Formula one
L (x, y, σ)=G (x, y, σ) * I (x, y) formula two
Wherein, G (x, y, σ) is that average is 0, and variance is σ2Normal distribution, I (x, y) is pending
Image, x and y are the two-dimensional coordinate of pending image, and σ is the standard deviation of Gaussian function.
L (x, y, σ) image of acquisition is set up into metric space using Gaussian function, Gauss difference image is obtained
D(x,y,σ).D (x, y, σ)=L (x, y, k σ)-L (x, y, σ), k are fixed coefficient.By Gaussian difference
Each pixel in image and its neighborhood, the neighborhood of its corresponding last layer image, the next tomographic image of correspondence
Neighborhood has 26 pixels altogether and compared, and such as its gray value is maximum or minimum, then record this point position and it
The yardstick at place, is used as key point.
Second, by four neighborhoods of key point obtain key point position gradient amplitude size m (x, y) and
Gradient direction θ (x, y).
The range of degrees of gradient direction is [0,360 °], and this scope is divided into 36 intervals, each interval
10 °, then form a histogram.The maximum interval of histogram intermediate value represents terraced in key point local neighborhood
The Main way of degree, maximum represents the amplitude size of gradient on this direction.In the present embodiment, statistics
Feature of the pixel of 16 × 16 contiguous ranges to describe its characteristic point, generates 16 (4 × 4) individual histograms, often
Individual histogram includes 8 features.So for each key point, being tieed up using 4 × 4 × 8=128 altogether
Special parameter is described so that each key point has position, residing yardstick and three, direction information, from
And determine a SIFT feature region.
After the SIFT feature Area generation of the image of acquisition, graphics processing unit 2 is by the SIFT of the image taken
Characteristic area is matched with the SIFT feature region in default respective image template.In the present embodiment,
It is used as the matching of key point in two images using the Euclidean distance of characteristic vector, the formula of matching is as follows：
Conf (x)=1-d1 (x)/d2 (x)
D1 (x) for key point in key point and default respective image template in the image that obtains minimum distance；
D2 (x) in key point and default respective image template in the image that obtains key point time closely.When
When conf (x) is less than given threshold, then it is assumed that two crucial Point matchings, when pass all in the image of acquisition
When key point is matched with key point all in default respective image template, it is believed that two width figures are matched.When adopting
Multiple figures of the object to be detected collected then think that the product is when being matched completely with default respective image template
It is qualified, as long as any one figure is mismatched, then it is assumed that object to be detected is defective work.
In summary, by setting multiple micro-cameras, compared with existing single CCD camera, due to
Each micro-camera can realize auto-focusing, in IMAQ without carrying out repeatedly adjusting micro-camera again
Focal length be that can be achieved to the disposable IMAQ of the object to be detected with different high low degrees, the setting
The speed of IMAQ is substantially increased, the process of IMAQ is reduced, so as to reach reduction testing cost
Purpose.The picture that multiple micro-cameras are obtained is handled by setting graphics processing unit, passed through
Judge that multiple images for getting are realized with different height from whether default respective image template matches respectively
The qualified detection of the detected article of low degree.
By setting the result after industrial computer and display, graphics processing unit to be shown by display,
It is easy to operator to observe.By setting the deliverying unit that is connected with industrial computer, deliverying unit is by defective work
Directly rejected from flowing water Working position, realize automatically screening.
Although the present invention is disclosed above by preferred embodiment, but is not limited to the present invention, any ripe
Know this those skilled in the art, without departing from the spirit and scope of the present invention, a little change and retouching can be made, therefore
Protection scope of the present invention is worked as to be defined depending on claims scope claimed.
Claims (9)
1. a kind of polyphaser vision detection system, it is characterised in that including：
Multiple micro-cameras, are arranged on around object to be detected, and multiple micro-cameras pass through auto-focusing
Mode obtains multiple images of object to be detected；
Graphics processing unit, is electrically connected with the multiple micro-camera, by multiple images got respectively with
Default respective image template is matched；When all images are with default respective image template matches,
The object to be detected is judged for certified products, otherwise, judges the object to be detected for defective work.
2. polyphaser vision detection system according to claim 1, it is characterised in that the polyphaser
Vision detection system also includes industrial computer and display, and industrial computer is connected with graphics processing unit, receives figure
As processing unit result and shown over the display.
3. polyphaser vision detection system according to claim 2, it is characterised in that the polyphaser
Vision detection system also includes the deliverying unit being connected with industrial computer, and industrial computer receives graphics processing unit
The defective work signal of output and by the signal output to deliverying unit, deliverying unit is by defective work from flowing water
Rejected on Working position.
4. polyphaser vision detection system according to claim 1, it is characterised in that the polyphaser
Vision detection system also includes memory module, and the memory module is electrically connected with described image processing unit, deposited
Store up image and data after graphics processing unit processing.
5. a kind of polyphaser visible detection method, it is characterised in that including：
Multiple micro-cameras obtain multiple images of object to be detected by way of auto-focusing；
Multiple images got are matched with default respective image template respectively；When all images are equal
During with default respective image template matches, the object to be detected is judged for certified products, otherwise, judges the quilt
Detection object is defective work.
6. camera visible detection method according to claim 5, it is characterised in that many by what is got
Opening the step of image is matched with default respective image template respectively includes：
For the every image got, the key point of the image is extracted；
Feature description is carried out to key point；
In the key point and default respective image template that image is obtained according to the feature profile matching of key point
Key point, when all key points in all key points and default respective image template for obtaining image are complete
During matching, it is believed that the image got and default respective image template matches.
7. camera visible detection method according to claim 6, it is characterised in that calculated using SIFT
Method extracts the key point of the every image got and carries out feature description to key point, and specific step is as follows：
The metric space of image is set up, the key point of image is searched in metric space, key point place is obtained
The position of pixel；
Gradient amplitude size m (x, y) and the gradient side of key point position are obtained by four neighborhoods of key point
It is that key point assigns 128 dimension parameters by amplitude size m (x, y) and gradient direction θ (x, y) to θ (x, y),
So that each key point has position, residing yardstick and three, direction information, so that it is determined that a SIFT feature
Region.
8. camera visible detection method according to claim 6, it is characterised in that special using key point
Levy the key point that vectorial Euclidean distance comes in key point and default respective image template to extraction image
Matching.
9. camera visible detection method according to claim 5, it is characterised in that the polyphaser is regarded
Feel that detection method also includes：Multiple images got are matched with default respective image template respectively
Judge to obtain the parameter of object to be detected by multiple images after whether object to be detected is qualified and deposited
Storage.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610048485.0A CN106996934A (en) | 2016-01-25 | 2016-01-25 | Polyphaser vision detection system and detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610048485.0A CN106996934A (en) | 2016-01-25 | 2016-01-25 | Polyphaser vision detection system and detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106996934A true CN106996934A (en) | 2017-08-01 |
Family
ID=59428214
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610048485.0A Pending CN106996934A (en) | 2016-01-25 | 2016-01-25 | Polyphaser vision detection system and detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106996934A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108982532A (en) * | 2018-08-23 | 2018-12-11 | 红塔烟草(集团)有限责任公司 | Plume polyphaser repeats vision inspection apparatus and method |
| CN113155865A (en) * | 2021-01-06 | 2021-07-23 | 天津大学 | Multi-camera-based aluminum die casting hole inner wall defect detection system and detection method |
| CN115855951A (en) * | 2022-11-26 | 2023-03-28 | 苏州三立检测技术有限公司 | Cloth cover flaw detection method and system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201116868Y (en) * | 2007-06-15 | 2008-09-17 | 山东省药用玻璃股份有限公司 | Tubular bottle on-line detecting system |
| CN102189333A (en) * | 2011-05-04 | 2011-09-21 | 苏州天弘激光股份有限公司 | Laser cutting machine with CCD automatic focusing system |
| CN102967983A (en) * | 2012-11-07 | 2013-03-13 | 苏州科达科技股份有限公司 | Automatic focusing method of camera |
| CN102984530A (en) * | 2011-09-02 | 2013-03-20 | 宏达国际电子股份有限公司 | Image processing system and automatic focusing method |
| CN103209306A (en) * | 2012-01-17 | 2013-07-17 | Lg伊诺特有限公司 | Camera Module, Auto Focus Method And Auto Focus Calibration Method |
| CN103350281A (en) * | 2013-06-20 | 2013-10-16 | 深圳市大族激光科技股份有限公司 | Automatic focusing device and automatic focusing method for laser marking machine |
| CN103376615A (en) * | 2012-04-24 | 2013-10-30 | 鸿富锦精密工业（深圳）有限公司 | Automatic focusing device and automatic focusing method |
| CN104118609A (en) * | 2014-07-22 | 2014-10-29 | 广东平航机械有限公司 | Labeling quality detecting method and device |
| CN104683685A (en) * | 2013-11-29 | 2015-06-03 | 光宝科技股份有限公司 | Automatic focusing method, automatic focusing device and image extracting device thereof |
| CN104949995A (en) * | 2015-07-02 | 2015-09-30 | 上海齐宏检测技术有限公司 | Online detection device and detection method thereof |
-
2016
- 2016-01-25 CN CN201610048485.0A patent/CN106996934A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201116868Y (en) * | 2007-06-15 | 2008-09-17 | 山东省药用玻璃股份有限公司 | Tubular bottle on-line detecting system |
| CN102189333A (en) * | 2011-05-04 | 2011-09-21 | 苏州天弘激光股份有限公司 | Laser cutting machine with CCD automatic focusing system |
| CN102984530A (en) * | 2011-09-02 | 2013-03-20 | 宏达国际电子股份有限公司 | Image processing system and automatic focusing method |
| CN103209306A (en) * | 2012-01-17 | 2013-07-17 | Lg伊诺特有限公司 | Camera Module, Auto Focus Method And Auto Focus Calibration Method |
| CN103376615A (en) * | 2012-04-24 | 2013-10-30 | 鸿富锦精密工业（深圳）有限公司 | Automatic focusing device and automatic focusing method |
| CN102967983A (en) * | 2012-11-07 | 2013-03-13 | 苏州科达科技股份有限公司 | Automatic focusing method of camera |
| CN103350281A (en) * | 2013-06-20 | 2013-10-16 | 深圳市大族激光科技股份有限公司 | Automatic focusing device and automatic focusing method for laser marking machine |
| CN104683685A (en) * | 2013-11-29 | 2015-06-03 | 光宝科技股份有限公司 | Automatic focusing method, automatic focusing device and image extracting device thereof |
| CN104118609A (en) * | 2014-07-22 | 2014-10-29 | 广东平航机械有限公司 | Labeling quality detecting method and device |
| CN104949995A (en) * | 2015-07-02 | 2015-09-30 | 上海齐宏检测技术有限公司 | Online detection device and detection method thereof |
Non-Patent Citations (2)
| Title |
|---|
| 张建民等: "用于CCD数码成像的自动对焦技术", 《天津工程师范学院学报》 * |
| 王欣等: "基于图像清晰度评价函数的CCD摄像机自动调焦技术研究", 《长春理工大学学报（自然科学版）》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108982532A (en) * | 2018-08-23 | 2018-12-11 | 红塔烟草(集团)有限责任公司 | Plume polyphaser repeats vision inspection apparatus and method |
| CN113155865A (en) * | 2021-01-06 | 2021-07-23 | 天津大学 | Multi-camera-based aluminum die casting hole inner wall defect detection system and detection method |
| CN115855951A (en) * | 2022-11-26 | 2023-03-28 | 苏州三立检测技术有限公司 | Cloth cover flaw detection method and system |
| CN115855951B (en) * | 2022-11-26 | 2025-12-02 | 苏州三立检测技术有限公司 | Fabric Defect Detection Methods and Systems |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8699786B2 (en) | 3D model generating apparatus, method and CRM by line pattern imaging | |
| CN111640157A (en) | A Neural Network-Based Checkerboard Corner Detection Method and Its Application | |
| CN117036641A (en) | Road scene three-dimensional reconstruction and defect detection method based on binocular vision | |
| CN109961399B (en) | Optimal suture line searching method based on image distance transformation | |
| CN102592147A (en) | Method and device for detecting human face | |
| CN111257329A (en) | A kind of smart phone camera defect detection method and detection system | |
| CN109741325B (en) | Intelligent detection method for wiring verticality | |
| EP2793172B1 (en) | Image processing apparatus, image processing method and program | |
| CN111353993A (en) | A method of thread angle measurement based on machine vision | |
| CN110335233A (en) | Express-way guard-rail plates defect detecting system and method based on image processing techniques | |
| CN104268602A (en) | Method and device for occluded workpiece recognition based on binary feature matching | |
| CN109559324A (en) | A kind of objective contour detection method in linear array images | |
| CN111665199A (en) | Wire and cable color detection and identification method based on machine vision | |
| CN115049689A (en) | Table tennis identification method based on contour detection technology | |
| CN119048837B (en) | A PCB board component defect detection method, system, equipment and medium | |
| CN106067031A (en) | Cooperate with the degree of depth learning network Machine Vision Recognition system based on artificial mechanism for correcting errors | |
| TW419634B (en) | Automatic detection system and method using bar code positioning | |
| CN106996934A (en) | Polyphaser vision detection system and detection method | |
| CN110866917A (en) | Tablet type and arrangement mode identification method based on machine vision | |
| CN108734054B (en) | Non-shielding citrus fruit image identification method | |
| CN116563229A (en) | Agricultural product defect detection method and system based on multi-view image feature fusion | |
| CN104484653A (en) | Bad corn kernel detecting method based on image recognition technology | |
| CN116029987A (en) | A welding quality detection method, device and electronic equipment | |
| CN106204889B (en) | A kind of localization method and device of bank note fluorescence area | |
| CN110345919B (en) | A space debris detection method based on 3D space vector and 2D plane coordinates |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170801 |