CN108280838A - A kind of intermediate plate tooth form defect inspection method based on edge detection - Google Patents
A kind of intermediate plate tooth form defect inspection method based on edge detection Download PDFInfo
- Publication number
- CN108280838A CN108280838A CN201810094780.9A CN201810094780A CN108280838A CN 108280838 A CN108280838 A CN 108280838A CN 201810094780 A CN201810094780 A CN 201810094780A CN 108280838 A CN108280838 A CN 108280838A
- Authority
- CN
- China
- Prior art keywords
- image
- intermediate plate
- tooth
- edge
- edge detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Abstract
The invention discloses a kind of intermediate plate tooth form defect inspection method based on edge detection, includes the following steps：（1）Intermediate plate workpiece image acquires and pretreatment；（2）Image template matching positioning and image cropping are carried out to workpiece；（3）Edge detection is carried out to image；（4）Medium filtering and Morphological scale-space are carried out to image；（5）It carries out feature extraction and differentiates.The present invention can be at plant produced line scene accurately to intermediate plate tooth form defect（Flat tooth, rotten tooth, weight tooth, tabula rasa）It is detected identification, efficiently solves the problems, such as that current artificial detection speed is slow, efficiency is low, of high cost, improves the production automation degree and product quality of intermediate plate, while the method for the present invention has the advantages that strong robustness.
Description
Technical field
The present invention relates to construction automatic measurement technique field more particularly to a kind of intermediate plate tooth forms based on edge detection
Defect inspection method.
Background technology
With the development of prestressed anchor technology, intermediate plate anchor (abbreviation intermediate plate) in prestressed anchor engineering get over by proportion
Come bigger, is widely used in the construction such as different types of rridges road skyscraper, intermediate plate is the weight of prestress anchorage system
One of basic part is wanted, the quality of working face tooth form quality directly affects the safety of prestressing force structures, if there is tooth form matter
If amount defect workpiece come into the market, may cause when serious building occur safety accident, greatly destroy social safety and
People's property equally brings great economic loss and liability exposure to manufacturing enterprise.
Therefore, link is very important to the detection of intermediate plate.The detection method used on production line at present is artificial mesh
Inspection is surveyed, and deficiency is：Detection speed is slow, it is less efficient, of high cost, be easy to cause human error detection.
Invention content
In view of the deficiencies of the prior art, present invention solves the technical problem that being how to solve that artificial detection speed is slow, efficiency
It is low, of high cost, be easy to cause the problem of human error.
In order to solve the above technical problems, technical solution provided by the invention is that a kind of intermediate plate tooth form based on edge detection is scarce
Detection method is fallen into, is included the following steps：
(1) acquisition of intermediate plate workpiece image and pretreatment；
(2) image template matching positioning and image cropping are carried out to workpiece；
(3) edge detection is carried out to image；
(4) medium filtering and Morphological scale-space are carried out to image；
(5) it carries out feature extraction and differentiates.
In step (1),
The intermediate plate workpiece image acquisition utilizes CCD industrial cameras by red bowl-type diffusing reflection light source orthodromic illumination
Acquire intermediate plate workpiece image with image pick-up card, workpiece image is RGB image, after workpiece image is transferred to host computer；
The pretreatment is adaptive, the enhancing picture contrast to the image collected progress gradation conversion and gray scale.
In step (2),
The positioning of described image template matches is the template matching algorithm based on shape feature, according to the gradient phase of object edge
Closing property carries out images match as matching criterior, by the template that testing image and standard picture generate, and obtains pressing from both sides in testing image
The relevant position parameter of piece；The location parameter obtained after being positioned further according to template matches carries out affine transformation and realizes intermediate plate in image
The translation of workpiece and rotation angle correction；
It is the cutting that 900x200 pixels are carried out to the image after positioning correction that described image, which is cut, obtains intermediate plate tooth form
Region ROI is to accelerate arithmetic speed and improve discrimination precision.
In step (3), average value processing is carried out to image before the progress edge detection to image, the edge detection is base
In the Image Edge-Detection of Canny operators, specific method is：
A) noise is eliminated, is 2D gaussian filterings template and original image convolution；
B) gradient operator such as Prewitt, Sobel is utilized to find gradation of image along horizontal and vertical derivative Gx、Gy, seek ladder
Degree：
C) direction of result calculating gradient b) is utilized：
D) direction at edge has been found out, so that it may the gradient direction at edge is roughly divided into 4 kinds：Horizontal, vertical, 45 degree of sides
To, 135 degree of directions, and the adjacent pixels in this pixel gradient direction can be found out；
E) traverse image, if the gray value of some pixel compared with the gray value of former and later two pixels on its gradient direction not
It is the largest, then the value of pixel is set to 0, i.e., is not edge；
F) detection of dual threashold value-based algorithm and connection edge.
In step (4),
The medium filtering particularly carries out 2x2 neighborhood medium filterings to the image after edge detection；
The Morphological scale-space is to carry out morphology processing to the image after segmentation, and specific processing procedure is to pass through
Structural element first applies intermediate plate image the closed operation in morphology, then corrodes expansion.
In step (5), the feature extraction and differentiation include the following steps：
A) data for analyzing all kinds of defect samples, obtain the decision rule of all kinds of defects：
Image Acquisition is carried out to a large amount of intermediate plate sample, the data of all kinds of defect samples are then obtained by image analysis,
And statistical analysis obtains the decision rule of all kinds of defects, establishes rule base, the Th in rule basehg1、ThPY、ThLYIt corresponds respectively to
The judgment threshold of qualified, flat tooth, rotten tooth, as unit of a numerical value of pixel；Thhg2、ThCY、ThGBCorrespond respectively to it is qualified,
The judgment threshold of weight tooth, tabula rasa, using the number of inside tapered thread tooth (edge to) as unit；
B) tooth form defects detection differentiates：
After image series of preprocessing and Image Edge-Detection, tooth form defects detection area is obtained using pixel counts method
The width mean pixel point numerical value Num of inside tapered thread tooth in the RIO of domainYK；Entire inner cone spiral shell is calculated to counting method using edge
The thread number Num of line facingYS；Mark is qualified, the diagnostic criterium of flat tooth, rotten tooth, weight tooth and tabula rasa is divided into HG, PY, LY, CY and
GB；Judge whether intermediate plate tooth form is qualified according to following two formula：
Judge intermediate plate with the presence or absence of flat tooth, rotten tooth defect according to following two formula：
Judge that intermediate plate whether there is weight tooth, tabula rasa defect according to following two formula：
In formula, defect dipoles threshold value Thhg1、Thhg2、ThPY、ThLY、ThCY、ThGBIt is determined by rule based judgment library, YES and NO divide
Not Biao Shi existing defects and be not present defect.
There is technical scheme of the present invention higher Detection accuracy and robustness, the accuracy rate of defects detection can reach
96%；It is good to the Edge Gradient Feature effect of intermediate plate thread based on the edge detection of Canny operators, accurate positioning, defect inspection
Survey with strong points, detection speed is fast, speed can reach 0.2 second every, be effectively improved intermediate plate work piece production automation journey
The quality of degree and product.
Description of the drawings
Fig. 1 is the principle of the present invention flow chart.
Specific implementation mode
The present invention is further illustrated with reference to the accompanying drawings and examples, but is not limitation of the invention.
Embodiment 1：
If Fig. 1 shows a kind of intermediate plate tooth form defect inspection method based on edge detection, include the following steps：
(1) acquisition of intermediate plate workpiece image and pretreatment；
(2) image template matching positioning and image cropping are carried out to workpiece；
(3) edge detection is carried out to image；
(4) medium filtering and Morphological scale-space are carried out to image；
(5) it carries out feature extraction and differentiates.
In step (1),
The intermediate plate workpiece image acquisition is to utilize CCD industry phases by red bowl-type diffusing reflection light source orthodromic illumination
Machine and image pick-up card acquire intermediate plate workpiece image, and workpiece image is RGB image, and workpiece image is then transferred to host computer；
The pretreatment is adaptive, the enhancing picture contrast to the image collected progress gradation conversion and gray scale.
In step (2),
The positioning of described image template matches is the template matching algorithm based on shape feature, according to the gradient phase of object edge
Closing property carries out images match as matching criterior, by the template that testing image and standard picture generate, and obtains pressing from both sides in testing image
The relevant position parameter of piece；The location parameter obtained after being positioned further according to template matches carries out affine transformation and realizes intermediate plate in image
The translation of workpiece and rotation angle correction.
Described image, which is cut, to be cut to the image after positioning correction, obtains intermediate plate tooth form region ROI to accelerate to transport
It calculates speed and improves discrimination precision.
In step (3),
Average value processing is carried out to image before the progress edge detection to image, the edge detection is calculated based on Canny
The Image Edge-Detection of son, specific method are：
A) noise is eliminated, is 2D gaussian filterings template and original image convolution；
B) gradient operator such as Prewitt, Sobel is utilized to find gradation of image along horizontal and vertical derivative Gx、Gy, seek ladder
Degree：
C) direction of result calculating gradient b) is utilized：
D) direction at edge has been found out, so that it may the gradient direction at edge is roughly divided into 4 kinds:Horizontal, vertical, 45 degree of sides
To, 135 degree of directions, and the adjacent pixels in this pixel gradient direction can be found out；
E) traverse image, if the gray value of some pixel compared with the gray value of former and later two pixels on its gradient direction not
It is the largest, then the value of pixel is set to 0, i.e., is not edge；
F) detection of dual threashold value-based algorithm and connection edge.
In step (4),
The medium filtering is to carry out medium filtering to the image after edge detection.
The Morphological scale-space is to carry out morphology processing to the image after segmentation, and processing procedure is to pass through structural elements
Element first applies intermediate plate image the closed operation in morphology, then corrodes expansion.
In step (5), the feature extraction and differentiation include the following steps：
A) data for analyzing all kinds of defect samples, obtain the decision rule of all kinds of defects：
Image Acquisition is carried out to a large amount of intermediate plate sample, the data of all kinds of defect samples are then obtained by image analysis,
And statistical analysis obtains the decision rule of all kinds of defects, establishes rule base, the Th in rule basehg1、ThPY、ThLYIt corresponds respectively to
The judgment threshold of qualified, flat tooth, rotten tooth, as unit of pixel numerical value；Thhg2、ThCY、ThGBIt is qualified, again to correspond respectively to
The judgment threshold of tooth, tabula rasa, using the number of inside tapered thread tooth (edge to) as unit.
B) tooth form defects detection differentiates：
After image series of preprocessing and Image Edge-Detection, tooth form defects detection area is obtained using pixel counts method
The width mean pixel point numerical value Num of inside tapered thread tooth in the RIO of domainYK；Entire inner cone spiral shell is calculated to counting method using edge
The thread number Num of line facingYS.Mark is qualified, the diagnostic criterium of flat tooth, rotten tooth, weight tooth and tabula rasa is divided into HG, PY, LY, CY and
GB.Judge whether intermediate plate tooth form is qualified according to following two formula：
Judge intermediate plate with the presence or absence of flat tooth, rotten tooth defect according to following two formula：
Judge that intermediate plate whether there is weight tooth, tabula rasa defect according to following two formula：
In formula, defect dipoles threshold value Thhg1、Thhg2、ThPY、ThLY、ThCY、ThGBIt is determined by rule based judgment library, YES and NO divide
Not Biao Shi existing defects and be not present defect.
Embodiment 2：
Defect characteristic is extracted, by number by the image processing algorithm in embodiment 1 according to the principle flow chart in Fig. 1
It is counted according to analysis, formulates decision rule library.
Overall procedure explanation：Intermediate plate workpiece to be checked is transferred to detection station, photoelectric sensor triggering by feed mechanism
Camera takes pictures and acquires a frame Image Real-time Transmission to industrial personal computer, and host computer carries out defects detection by defects detection algorithm, and
Testing result is sent to slave computer by serial communication.Slave computer rejects defective work according to inspection result, and certified products will
Into next process, the final intelligent sorting for realizing workpiece.
The problem that present invention efficiently solves current artificial detection speed is slow, efficiency is low, of high cost, while having to first
Beginningization is insensitive, has the advantages that strong robustness, improves the production automation degree and product quality of intermediate plate.
Technical scheme of the present invention is explained in detail above in association with attached drawing, but the present invention is not limited to described reality
Apply mode.For a person skilled in the art, without departing from the principles and spirit of the present invention, these are implemented
Mode carries out various change, modification, replacement and modification, still falls within the scope of the present invention.
Claims (6)
1. a kind of intermediate plate tooth form defect inspection method based on edge detection, it is characterised in that：Include the following steps：
(1) acquisition of intermediate plate workpiece image and pretreatment；
(2) image template matching positioning and image cropping are carried out to workpiece；
(3) edge detection is carried out to image；
(4) medium filtering and Morphological scale-space are carried out to image
(5) it carries out feature extraction and differentiates.
2. the intermediate plate tooth form defect inspection method according to claim 1 based on edge detection, it is characterised in that：Step
(1) in,
Intermediate plate workpiece image acquisition be by red bowl-type diffusing reflection light source orthodromic illumination, using CCD industrial cameras and
Image pick-up card acquires intermediate plate workpiece image, and workpiece image is RGB image, and workpiece image is then transferred to host computer；
The pretreatment is adaptive, the enhancing picture contrast to the image collected progress gradation conversion and gray scale.
3. the intermediate plate tooth form defect inspection method according to claim 1 or 2 based on edge detection, it is characterised in that：Step
Suddenly in (2),
The positioning of described image template matches is the template matching algorithm based on shape feature, according to the gradient correlation of object edge
As matching criterior, the template that testing image and standard picture generate is subjected to images match, obtains intermediate plate in testing image
Relevant position parameter；The location parameter obtained after being positioned further according to template matches carries out affine transformation and realizes intermediate plate workpiece in image
Translation and rotation angle correction；
It is the cutting that 900x200 pixels are carried out to the image after positioning correction that described image, which is cut, obtains intermediate plate tooth form region
ROI is to accelerate arithmetic speed and improve discrimination precision.
4. the intermediate plate tooth form defect inspection method according to claim 1 or 2 based on edge detection, it is characterised in that：Step
Suddenly in (3), average value processing is carried out to image before carrying out edge detection to image, edge detection is the image based on Canny operators
Edge detection, specific method are：
A) noise is eliminated, is 2D gaussian filterings template and original image convolution；
B) gradient operator such as Prewitt, Sobel is utilized to find gradation of image along horizontal and vertical derivative Gx、Gy, seek gradient：
C) direction of result calculating gradient b) is utilized：
D) direction at edge has been found out, so that it may the gradient direction at edge is roughly divided into 4 kinds:Horizontal, vertical, 45 degree of directions,
135 degree of directions, and the adjacent pixels in this pixel gradient direction can be found out；
E) image is traversed, if the gray value of some pixel is not most compared with the gray value of former and later two pixels on its gradient direction
Big, pixel value is set to 0 by that, i.e., is not edge；
F) detection of dual threashold value-based algorithm and connection edge.
5. the intermediate plate tooth form defect inspection method according to claim 1 or 2 based on edge detection, it is characterised in that：Step
Suddenly in (4),
The medium filtering is to carry out medium filtering to the image after edge detection；
The Morphological scale-space is to carry out morphology processing to the image after segmentation, and processing procedure is by structural element pair
Intermediate plate image first applies the closed operation in morphology, then corrodes expansion.
6. the intermediate plate tooth form defect inspection method according to claim 1 or 2 based on edge detection, it is characterised in that：Step
Suddenly in (5), the feature extraction and differentiation include the following steps：
A) data for analyzing all kinds of defect samples, obtain the decision rule of all kinds of defects：
Image Acquisition is carried out to a large amount of intermediate plate sample, the data of all kinds of defect samples are then obtained by image analysis, and unite
Meter analysis obtains the decision rule of all kinds of defects, establishes rule base, the Th in rule basehg1、ThPY、ThLYIt corresponds respectively to close
The judgment threshold of lattice, flat tooth, rotten tooth, as unit of pixel numerical value；Thhg2、ThCY、ThGBCorrespond respectively to qualified, weight tooth,
The judgment threshold of tabula rasa, using the number of inside tapered thread tooth (edge to) as unit；
B) tooth form defects detection differentiates：
After image series of preprocessing and Image Edge-Detection, tooth form defects detection region is obtained using pixel counts method
The width mean pixel point numerical value Num of inside tapered thread tooth in RIOYK；Entire inside tapered thread is calculated to counting method using edge
The thread number Num of facingYS；Mark is qualified, the diagnostic criterium of flat tooth, rotten tooth, weight tooth and tabula rasa is divided into HG, PY, LY, CY and
GB；Judge whether intermediate plate tooth form is qualified according to following formula：
Judge intermediate plate with the presence or absence of flat tooth, rotten tooth defect according to following two formula：
Judge that intermediate plate whether there is weight tooth, tabula rasa defect according to following two formula：
In formula, defect dipoles threshold value Thhg1、Thhg2、ThPY、ThLY、ThCY、ThGBIt is determined by rule based judgment library, YES and NO distinguish table
Show existing defects and defect is not present.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810094780.9A CN108280838A (en) | 2018-01-31 | 2018-01-31 | A kind of intermediate plate tooth form defect inspection method based on edge detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810094780.9A CN108280838A (en) | 2018-01-31 | 2018-01-31 | A kind of intermediate plate tooth form defect inspection method based on edge detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108280838A true CN108280838A (en) | 2018-07-13 |
Family
ID=62807112
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810094780.9A Pending CN108280838A (en) | 2018-01-31 | 2018-01-31 | A kind of intermediate plate tooth form defect inspection method based on edge detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108280838A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109011654A (en) * | 2018-09-05 | 2018-12-18 | 浙江大丰实业股份有限公司 | Peoperty walking identification mechanism |
| CN109598605A (en) * | 2018-11-26 | 2019-04-09 | 格锐科技有限公司 | A kind of long-distance intelligent assessment and loan self-aid system based on entity guaranty |
| CN109816652A (en) * | 2019-01-25 | 2019-05-28 | 湖州云通科技有限公司 | A kind of intricate casting defect identification method based on gray scale conspicuousness |
| CN111798479A (en) * | 2020-06-30 | 2020-10-20 | 中铁二局集团有限公司 | Core drilling sampling data processing method and system |
| CN113628251A (en) * | 2021-10-11 | 2021-11-09 | 北京中科金马科技股份有限公司 | Smart hotel terminal monitoring method |
| CN116596932A (en) * | 2023-07-18 | 2023-08-15 | 北京阿丘机器人科技有限公司 | Method, device, equipment and storage medium for detecting appearance of battery top cover pole |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105976352A (en) * | 2016-04-14 | 2016-09-28 | 北京工业大学 | Weld seam surface detect feature extraction method based on grayscale image morphology |
| CN106353324A (en) * | 2016-08-10 | 2017-01-25 | 浙江理工大学 | Magnet ring surface defect extraction method |
| CN106372645A (en) * | 2016-08-29 | 2017-02-01 | 广东工业大学 | Mobile phone housing complex texture background defect detection method |
| CN107169979A (en) * | 2017-05-11 | 2017-09-15 | 南宁市正祥科技有限公司 | A kind of method for detecting image edge of improvement Canny operators |
| CN107490583A (en) * | 2017-09-12 | 2017-12-19 | 桂林电子科技大学 | A kind of intermediate plate defect inspection method based on machine vision |
-
2018
- 2018-01-31 CN CN201810094780.9A patent/CN108280838A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105976352A (en) * | 2016-04-14 | 2016-09-28 | 北京工业大学 | Weld seam surface detect feature extraction method based on grayscale image morphology |
| CN106353324A (en) * | 2016-08-10 | 2017-01-25 | 浙江理工大学 | Magnet ring surface defect extraction method |
| CN106372645A (en) * | 2016-08-29 | 2017-02-01 | 广东工业大学 | Mobile phone housing complex texture background defect detection method |
| CN107169979A (en) * | 2017-05-11 | 2017-09-15 | 南宁市正祥科技有限公司 | A kind of method for detecting image edge of improvement Canny operators |
| CN107490583A (en) * | 2017-09-12 | 2017-12-19 | 桂林电子科技大学 | A kind of intermediate plate defect inspection method based on machine vision |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109011654A (en) * | 2018-09-05 | 2018-12-18 | 浙江大丰实业股份有限公司 | Peoperty walking identification mechanism |
| CN109011654B (en) * | 2018-09-05 | 2020-05-29 | 浙江大丰实业股份有限公司 | Stage property walking identification mechanism |
| CN109598605A (en) * | 2018-11-26 | 2019-04-09 | 格锐科技有限公司 | A kind of long-distance intelligent assessment and loan self-aid system based on entity guaranty |
| CN109816652A (en) * | 2019-01-25 | 2019-05-28 | 湖州云通科技有限公司 | A kind of intricate casting defect identification method based on gray scale conspicuousness |
| CN109816652B (en) * | 2019-01-25 | 2022-08-12 | 湖州云通科技有限公司 | Complex casting defect identification method based on gray level significance |
| CN111798479A (en) * | 2020-06-30 | 2020-10-20 | 中铁二局集团有限公司 | Core drilling sampling data processing method and system |
| CN111798479B (en) * | 2020-06-30 | 2024-01-23 | 中铁二局集团有限公司 | Drill core sampling data processing method and system |
| CN113628251A (en) * | 2021-10-11 | 2021-11-09 | 北京中科金马科技股份有限公司 | Smart hotel terminal monitoring method |
| CN116596932A (en) * | 2023-07-18 | 2023-08-15 | 北京阿丘机器人科技有限公司 | Method, device, equipment and storage medium for detecting appearance of battery top cover pole |
| CN116596932B (en) * | 2023-07-18 | 2024-02-09 | 北京阿丘机器人科技有限公司 | Method, device, equipment and storage medium for detecting appearance of battery top cover pole |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108280838A (en) | A kind of intermediate plate tooth form defect inspection method based on edge detection | |
| CN106290388B (en) | A kind of insulator breakdown automatic testing method | |
| CN110648364B (en) | Multi-dimensional space solid waste visual detection positioning and identification method and system | |
| CN107490583A (en) | A kind of intermediate plate defect inspection method based on machine vision | |
| CN108760747A (en) | A kind of 3D printing model surface defect visible detection method | |
| CN111951237A (en) | Visual appearance detection method | |
| CN109598715B (en) | Material granularity online detection method based on machine vision | |
| CN106969706A (en) | Workpiece sensing and three-dimension measuring system and detection method based on binocular stereo vision | |
| CN106780526A (en) | A kind of ferrite wafer alligatoring recognition methods | |
| WO2021109697A1 (en) | Character segmentation method and apparatus, and computer-readable storage medium | |
| CN110296997A (en) | The defect inspection method and device of ceramic tile based on machine vision | |
| CN112149543B (en) | Building dust recognition system and method based on computer vision | |
| CN104537651B (en) | Proportion detecting method and system for cracks in road surface image | |
| CN109685766A (en) | A kind of Fabric Defect detection method based on region fusion feature | |
| CN106824806A (en) | The detecting system and detection method of the low module plastic gear based on machine vision | |
| CN109859160A (en) | Almag internal defect in cast image-recognizing method based on machine vision | |
| CN110189375A (en) | A kind of images steganalysis method based on monocular vision measurement | |
| CN104034638A (en) | Diamond wire particle online quality inspection method based on machine vision | |
| CN111122590A (en) | Ceramic surface defect detection device and detection method | |
| CN106780437B (en) | A kind of quick QFN chip plastic packaging image obtains and amplification method | |
| CN116228771B (en) | Visual analysis-based mineral material machine tool casting detection method | |
| CN104034637B (en) | Based on the online quality inspection device of diamond wire particle of machine vision | |
| CN110807763A (en) | Method and system for detecting ceramic tile surface bulge | |
| CN107220946B (en) | Real-time removing method for bad block degree images on rock conveyer belt | |
| CN107564001B (en) | Magnetic sheet corner defect detection method based on pit search |
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 |
Application publication date: 20180713 |
|
| RJ01 | Rejection of invention patent application after publication |