CN107146246A - One kind is used for workpiece machining surface background texture suppressing method - Google Patents
One kind is used for workpiece machining surface background texture suppressing method Download PDFInfo
- Publication number
- CN107146246A CN107146246A CN201710317857.XA CN201710317857A CN107146246A CN 107146246 A CN107146246 A CN 107146246A CN 201710317857 A CN201710317857 A CN 201710317857A CN 107146246 A CN107146246 A CN 107146246A
- Authority
- CN
- China
- Prior art keywords
- workpiece surface
- block
- pixels
- image
- feature
- 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
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- 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
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
One kind is used in workpiece surface quality image detecting technique process background texture suppressing method, and its drip irrigation device is:IMAQ is carried out to workpiece surface by professional imaging device first and gray processing is handled, workpiece surface gray level image is obtained;It is then based on gray level co-occurrence matrixes generation workpiece surface gray feature figure;Travel through workpiece surface gray feature image vegetarian refreshments, and workpiece surface gray feature figure is divided into several N × N (N ∈ { 3 as central pixel point successively, 5 }) the block of pixels of size, random sampling block of pixels, by sample vector and Non-negative Matrix Factorization is carried out, obtain processing background textural characteristics figure;Processing background textural characteristics figure and the Euclidean distance of each block of pixels in workpiece surface gray feature figure are calculated successively, average and be assigned to the central pixel point of respective pixel block in workpiece surface gray feature figure, realize that workpiece surface image processing background texture suppresses, highlight workpiece surface quality feature.
Description
Technical field
Background texture suppressing method is processed in workpiece surface quality image detecting technique the present invention relates to one kind, belongs to work
Part surface quality detection field.
Background technology
With the development of manufacturing technology, high cost, high-precision batch machining part are more and more, and workpiece surface quality is examined
Survey proposes higher requirement.The new suppressing method for workpiece surface background texture of research and development, and then realize workpiece surface matter
Amount detection, meets the active demand of enterprise, also significant to mechanical subject fundamental research.
In machine cut process, always domestic and international is detected to workpiece surface quality defect from image angle
Study hotspot.Due to the regularity of cutter operation, workpiece to be machined surface can leave the machining texture of certain orientation;With
This simultaneously as machine vibration, cutting collision and workpiece material it is uneven in terms of reason, can cause workpiece surface produce split
The various defects such as line, cut, pockmark.On the one hand the presence of machining texture can provide reflection cutting process
Information, on the other hand can also interfere with the detection of Surface Flaw, using workpiece surface process background texture suppressing method pair
The problem of workpiece surface background texture is suppressed just solve machining interference of texture Surface Flaw Detection.
The content of the invention
It is an object of the invention to provide a kind of image analysis result and the physical detection result goodness of fit are higher, practicality is stronger
Be used in workpiece surface quality image detecting technique process background texture suppressing method, you can realize workpiece machining surface carry on the back
The suppression of scape texture, or the research of workpiece machining surface background texture provide theoretical foundation.
The technical solution adopted for the present invention to solve the technical problems is:One kind is in workpiece surface quality image detecting technique
Middle processing background texture suppressing method, the workpiece machining surface includes drilling, milling, turning, grinding workpiece surface, its
It is characterized in:IMAQ is carried out to workpiece surface by professional imaging device first and gray processing is handled, workpiece surface ash is obtained
Spend image;It is then based on gray level co-occurrence matrixes generation workpiece surface gray feature figure;Travel through workpiece surface gray feature image element
Point, and workpiece surface gray feature figure is divided into several N × N (N ∈ { 3,5 }) sizes as central pixel point successively
Block of pixels, random sampling block of pixels by sample vector and carries out Non-negative Matrix Factorization, obtains processing background textural characteristics figure;
Processing background textural characteristics figure and the Euclidean distance of each block of pixels in workpiece surface gray feature figure are calculated successively, are averaging
It is worth and is assigned to the central pixel point of respective pixel block in workpiece surface gray feature figure, realizes that workpiece surface image processes background
Texture suppresses, and highlights workpiece surface quality feature.
It is described to refer to set a M × M (M ∈ { 3,5 }) based on gray level co-occurrence matrixes generation workpiece surface gray feature figure
The detection window of size, then travels through workpiece surface gray level image pixel and locks successively in workpiece surface gray level image by M × M
The block of pixels of (M ∈ { 3,5 }) individual pixel composition, generates gray level co-occurrence matrixes, and element value in gray level co-occurrence matrixes is done into normalizing
Change is handled, and calculates Variance feature value according to obtained gray level co-occurrence matrixes, obtained Variance feature value is assigned into block of pixels
Detection window, is then moved to next position and repeats the above steps, until entire image has been traveled through by central pixel point successively
Untill.
The traversal workpiece surface gray feature image vegetarian refreshments, and it is as central pixel point that workpiece surface gray scale is special successively
Levy figure and be divided into the block of pixels of several N × N (N ∈ { 3,5 }) sizes and refer to set N × N (N ∈ { 3,5 }) size
Detection window, then travels through workpiece surface gray feature image vegetarian refreshments and locks successively in workpiece surface gray level image by N × N (N
∈ { 3,5 }) individual pixel composition block of pixels, intercept the block of pixels, detection window be then moved to next position simultaneously successively
Repeat the above steps, untill entire image has been traveled through.
The random sampling block of pixels, by sample vector and carries out Non-negative Matrix Factorization, obtains processing background texture special
Levy figure to refer in workpiece machining surface gray feature figure, the gray feature for representing defect accounts for smaller, basic based on statistics
Principle, a number of block of pixels is randomly selected in some width N × N (N ∈ { 3,5 }) of interception block of pixels can approximate generation
For the processing background textural characteristics of workpiece machining surface gray feature figure, the reduction figure then having using Non-negative Matrix Factorization
As redundancy, the ability of image substantive characteristics is obtained, after block of pixels vectorization, Non-negative Matrix Factorization is carried out as input, obtains
Process background textural characteristics figure.
The processing background textural characteristics figure refers to sampled pixel block after Non-negative Matrix Factorization, obtained basic matrix correspondence
Image.
It is described to calculate processing background textural characteristics figure and the Europe of each block of pixels in workpiece surface gray feature figure successively
Family name's distance, the central pixel point averaged and be assigned to respective pixel block in workpiece surface gray feature figure refers to machining back
Each column vector of the corresponding matrix of scape texture maps lines up a square formation by row, obtains several square formations, traversal workpiece surface ash
Characteristic pattern block of pixels is spent, the Euclidean between a block of pixels in these square formations and workpiece surface gray feature figure is then calculated successively
Distance, averages and is assigned to the block of pixels, repeat the above steps, until having traveled through all pixels block.
The beneficial effects of the invention are as follows:The present invention is a kind of gray level co-occurrence matrixes algorithm that is based on to workpiece surface gray level image
Textural characteristics be described, and utilize Algorithms of Non-Negative Matrix Factorization, processing background textural characteristics figure decomposited, to realize workpiece
The suppression of finished surface background texture, highlights workpiece surface quality feature.Traditional calculation is solved using Algorithms of Non-Negative Matrix Factorization
The problem of method can not carry out unsupervised learning image potential feature.In addition, based on gray level co-occurrence matrixes to image texture characteristic
Description method is simple and reliable, simplifies the analysis process of complexity.Proved by testing:Image analysis result is kissed with actual result
Close, accuracy rate is high, practical, can be widely applied to cutting quality detection field.
Brief description of the drawings
Fig. 1 is the principle flow chart of the present invention.
Fig. 2 is workpiece machining surface figure.
Fig. 3 is workpiece surface gray level image.
Fig. 4 is workpiece surface gray feature figure.
Fig. 5 is workpiece surface gray feature sample image.
Fig. 6 is work pieces process background texture characteristic pattern.
Fig. 7 is workpiece machining surface background texture suppression figure.
Embodiment
The present invention is described in further details with reference to the accompanying drawings and examples.
The present invention can be for the processing workpiece surface image such as drilling, milling, turning, grinding, so that Milling Process is tested as an example.
Embodiment 1, the workpiece machining surface includes drilling, milling, turning, grinding workpiece surface, it is characterized in that:
IMAQ is carried out to workpiece surface by professional imaging device first and gray processing is handled, workpiece surface gray level image is obtained;
It is then based on gray level co-occurrence matrixes generation workpiece surface gray feature figure;Traversal workpiece surface gray feature image vegetarian refreshments, and according to
The secondary block of pixels that workpiece surface gray feature figure is divided into several N × N (N ∈ { 3,5 }) sizes as central pixel point,
Random sampling block of pixels, by sample vector and carries out Non-negative Matrix Factorization, obtains processing background textural characteristics figure;Calculate successively
Background textural characteristics figure and the Euclidean distance of each block of pixels in workpiece surface gray feature figure are processed, is averaged and assignment
To the central pixel point of respective pixel block in workpiece surface gray feature figure, the processing background texture suppression of workpiece surface image is realized
System, highlights workpiece surface quality feature.Refering to Fig. 1 to Fig. 7.
Embodiment 2, it is described to refer to set M × M (M based on gray level co-occurrence matrixes generation workpiece surface gray feature figure
∈ { 3,5 }) size detection window, then travel through workpiece surface gray level image pixel lock workpiece surface gray level image successively
In by M × M (M ∈ { 3,5 }) individual pixels composition block of pixels, generate gray level co-occurrence matrixes, and by element in gray level co-occurrence matrixes
Value does normalized, calculates Variance feature value according to obtained gray level co-occurrence matrixes, obtained Variance feature value is assigned to
Detection window, is then moved to next position and repeats the above steps, until view picture figure by the central pixel point of block of pixels successively
Untill as having traveled through.Refering to Fig. 1 to Fig. 7, remaining be the same as Example 1.
Embodiment 3, the traversal workpiece surface gray feature image vegetarian refreshments, and successively as central pixel point by workpiece table
Face gray feature figure be divided into several N × N (N ∈ { 3,5 }) sizes block of pixels refer to set N × N (N ∈ 3,
5 }) the detection window of size, then travels through workpiece surface gray feature image vegetarian refreshments and locks successively in workpiece surface gray level image
By the block of pixels of the individual pixel compositions of N × N (N ∈ { 3,5 }), the block of pixels is intercepted, is then moved to detection window successively next
Individual position simultaneously repeats the above steps, untill entire image has been traveled through.Refering to Fig. 1 to Fig. 7, remaining same above-described embodiment.
Embodiment 4, the random sampling block of pixels by sample vector and carries out Non-negative Matrix Factorization, obtains machining back
Scape textural characteristics figure refers to that in workpiece machining surface gray feature figure the gray feature for representing defect accounts for smaller, based on system
Meter learns general principle, and a number of block of pixels is randomly selected in some width N × N (N ∈ { 3,5 }) of interception block of pixels
The processing background textural characteristics of workpiece machining surface gray feature figure can be approximately replaced, are then had using Non-negative Matrix Factorization
Reduction image redundancy, obtain the ability of image substantive characteristics, after block of pixels vectorization, be used as input to carry out nonnegative matrix point
Solution, obtains processing background textural characteristics figure.Refering to Fig. 1 to Fig. 7, remaining same above-described embodiment.
Embodiment 5, the processing background textural characteristics figure refers to sampled pixel block after Non-negative Matrix Factorization, obtained base
The corresponding image of matrix.Refering to Fig. 1 to Fig. 7, remaining same above-described embodiment.
Embodiment 6, it is described to calculate processing background textural characteristics figure and each picture in workpiece surface gray feature figure successively
The Euclidean distance of plain block, the central pixel point averaged and be assigned to respective pixel block in workpiece surface gray feature figure refers to
Each column vector of the corresponding matrix of processing background texture maps is lined up into a square formation by row, several square formations is obtained, travels through work
Part surface gray feature figure block of pixels, then calculate successively in these square formations and workpiece surface gray feature figure a block of pixels it
Between Euclidean distance, average and be assigned to the block of pixels, repeat the above steps, until traveled through all pixels block.Refer to
Fig. 1 to Fig. 7, remaining same above-described embodiment.
Embodiment 7, detailed process is as follows:
As shown in Figure 1, this figure is principle of the invention flow chart.Finished work surface is schemed by image capture device
As collection, obtain workpiece machining surface image and carry out gray processing processing, obtain workpiece surface gray level image;It is then based on gray scale
Co-occurrence matrix generates workpiece surface gray feature figure;Then workpiece surface gray feature image vegetarian refreshments is traveled through, and is used as successively
Workpiece surface gray feature figure is divided into the block of pixels of several N × N (N ∈ { 3,5 }) sizes, random sampling by imago vegetarian refreshments
Block of pixels, by sample vector and carries out Non-negative Matrix Factorization, obtains processing background textural characteristics figure;By calculating these successively
The Euclidean distance of square formation and a block of pixels in workpiece surface gray feature figure, averages and is assigned to the block of pixels, repeats
Above-mentioned steps, until having traveled through the suppression that all pixels block realizes workpiece machining surface image texture background.
As shown in Figure 2, it is the workpiece machining surface image collected by image capture device.Due to image into
As quality has an impact to subsequent treatment result, therefore the higher technical grade camera of pixel should be selected and preferable in conditions of exposure
IMAQ is carried out under environment.
Workpiece surface gray feature figure is generated based on gray level co-occurrence matrixes, as shown in accompanying drawing 3,4, this figure is workpiece surface side
Poor characteristic image, what it is due to variance reflection is each pixel value and the gray scale difference size of the area pixel average in region, and workpiece adds
The pixel grey scale difference in manufacturing deficiency region and processing normal region is undoubtedly very big in work surface, therefore workpiece surface variance is special
Levying figure can highlight at manufacturing deficiency edge well.
As shown in Figure 5, this figure is workpiece machining surface gray feature sample image, by special in workpiece machining surface gray scale
Levy in figure, the gray feature for representing defect accounts for smaller, based on statistics general principle, in some width N × N (N ∈ of interception
{ 3,5 }) a number of block of pixels is randomly selected in block of pixels can approximately replace adding for workpiece machining surface gray feature figure
Work background texture feature.
As shown in Figure 6, this figure is processing background textural characteristics figure, in order to reduce the redundancy of image array, is obtained more
Sparse expression way, using Algorithms of Non-Negative Matrix Factorization, decomposites the background of workpiece machining surface gray feature sample image
Feature, is used as the approximate description of processing background textural characteristics.
Last calculate successively of the invention processes background textural characteristics figure and each pixel in workpiece surface gray feature figure
The Euclidean distance of block, averages and is assigned to the central pixel point of respective pixel block in workpiece surface gray feature figure, realizes
Workpiece surface image processing background texture suppresses.Refering to Fig. 1 to Fig. 7, remaining same above-described embodiment.
Claims (6)
1. one kind is used in workpiece surface quality image detecting technique process background texture suppressing method, the workpiece machining surface
Including drilling, milling, turning, grinding workpiece surface, it is characterized in that:Workpiece surface is entered by professional imaging device first
Row IMAQ and gray processing processing, obtain workpiece surface gray level image;It is then based on gray level co-occurrence matrixes generation workpiece surface
Gray feature figure;Workpiece surface gray feature image vegetarian refreshments is traveled through, and it is as central pixel point that workpiece surface gray scale is special successively
Levy the block of pixels that figure is divided into several N × N (N ∈ { 3,5 }) sizes, random sampling block of pixels by sample vector and is carried out
Non-negative Matrix Factorization, obtains processing background textural characteristics figure;Processing background textural characteristics figure and workpiece surface gray scale are calculated successively
The Euclidean distance of the block of pixels of each in characteristic pattern, averages and is assigned to respective pixel block in workpiece surface gray feature figure
Central pixel point, realize workpiece surface image processing background texture suppress, highlight workpiece surface quality feature.
2. it is used in workpiece surface quality image detecting technique process background texture suppressing method according to claim 1, its
It is characterized in:It is described to refer to set a M × M (M ∈ { 3,5 }) based on gray level co-occurrence matrixes generation workpiece surface gray feature figure
The detection window of size, then travels through workpiece surface gray level image pixel and locks successively in workpiece surface gray level image by M × M
The block of pixels of (M ∈ { 3,5 }) individual pixel composition, generates gray level co-occurrence matrixes, and element value in gray level co-occurrence matrixes is done into normalizing
Change is handled, and calculates Variance feature value according to obtained gray level co-occurrence matrixes, obtained Variance feature value is assigned into block of pixels
Detection window, is then moved to next position and repeats the above steps, until entire image has been traveled through by central pixel point successively
Untill.
3. it is used in workpiece surface quality image detecting technique process background texture suppressing method according to claim 1, its
It is characterized in:The traversal workpiece surface gray feature image vegetarian refreshments, and it is as central pixel point that workpiece surface gray scale is special successively
Levy figure and be divided into the block of pixels of several N × N (N ∈ { 3,5 }) sizes and refer to set N × N (N ∈ { 3,5 }) size
Detection window, then travels through workpiece surface gray feature image vegetarian refreshments and locks successively in workpiece surface gray level image by N × N (N
∈ { 3,5 }) individual pixel composition block of pixels, intercept the block of pixels, detection window be then moved to next position simultaneously successively
Repeat the above steps, untill entire image has been traveled through.
4. it is used in workpiece surface quality image detecting technique process background texture suppressing method according to claim 1, its
It is characterized in:The random sampling block of pixels, by sample vector and carries out Non-negative Matrix Factorization, obtains processing background textural characteristics
Figure refers to that in workpiece machining surface gray feature figure the gray feature for representing defect accounts for smaller, substantially former based on statistics
Manage, randomly selecting a number of block of pixels in some width N × N (N ∈ { 3,5 }) of interception block of pixels can approximately replace
The processing background textural characteristics of workpiece machining surface gray feature figure, the reduction image then having using Non-negative Matrix Factorization
Redundancy, obtains the ability of image substantive characteristics, after block of pixels vectorization, carries out Non-negative Matrix Factorization as input, is added
Work background texture characteristic pattern.
5. it is used in workpiece surface quality image detecting technique process background texture suppressing method according to claim 1, its
It is characterized in:The processing background textural characteristics figure refers to sampled pixel block after Non-negative Matrix Factorization, obtained basic matrix correspondence
Image.
6. it is used in workpiece surface quality image detecting technique process background texture suppressing method according to claim 1, its
It is characterized in:It is described to calculate processing background textural characteristics figure and the Euclidean of each block of pixels in workpiece surface gray feature figure successively
Distance, the central pixel point averaged and be assigned to respective pixel block in workpiece surface gray feature figure refers to that background will be processed
Each column vector of the corresponding matrix of texture maps lines up a square formation by row, obtains several square formations, travels through workpiece surface gray scale
Characteristic pattern block of pixels, then calculate successively Euclidean in these square formations and workpiece surface gray feature figure between a block of pixels away from
From averaging and be assigned to the block of pixels, repeat the above steps, until traveled through all pixels block.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710317857.XA CN107146246A (en) | 2017-05-08 | 2017-05-08 | One kind is used for workpiece machining surface background texture suppressing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710317857.XA CN107146246A (en) | 2017-05-08 | 2017-05-08 | One kind is used for workpiece machining surface background texture suppressing method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107146246A true CN107146246A (en) | 2017-09-08 |
Family
ID=59778571
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710317857.XA Pending CN107146246A (en) | 2017-05-08 | 2017-05-08 | One kind is used for workpiece machining surface background texture suppressing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107146246A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108734663A (en) * | 2018-05-30 | 2018-11-02 | 北京电子工程总体研究所 | A kind of target's center's display methods and system based on location information |
CN110309855A (en) * | 2019-05-30 | 2019-10-08 | 上海联影智能医疗科技有限公司 | Training method, computer equipment and the storage medium of image segmentation |
CN116486116A (en) * | 2023-06-16 | 2023-07-25 | 济宁大爱服装有限公司 | Machine vision-based method for detecting abnormality of hanging machine for clothing processing |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104376529A (en) * | 2014-11-25 | 2015-02-25 | 深圳北航新兴产业技术研究院 | Gray level image colorization system and method based on GLCM |
CN105844278A (en) * | 2016-04-15 | 2016-08-10 | 浙江理工大学 | Multi-feature fused fabric scanning pattern recognition method |
-
2017
- 2017-05-08 CN CN201710317857.XA patent/CN107146246A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104376529A (en) * | 2014-11-25 | 2015-02-25 | 深圳北航新兴产业技术研究院 | Gray level image colorization system and method based on GLCM |
CN105844278A (en) * | 2016-04-15 | 2016-08-10 | 浙江理工大学 | Multi-feature fused fabric scanning pattern recognition method |
Non-Patent Citations (3)
Title |
---|
韦衍: "工件表面质量缺陷的无损视觉检测关键技术研究", 《万方数据知识服务平台》 * |
魏建亮 等: "基于灰度共生矩阵的车刀车削工件表面纹理分析", 《机械制造与自动化》 * |
黎志: "非负矩阵分解在遥感图像变化检测中的应用研究", 《万方数据知识服务平台》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108734663A (en) * | 2018-05-30 | 2018-11-02 | 北京电子工程总体研究所 | A kind of target's center's display methods and system based on location information |
CN108734663B (en) * | 2018-05-30 | 2022-05-20 | 北京电子工程总体研究所 | Target center display method and system based on position information |
CN110309855A (en) * | 2019-05-30 | 2019-10-08 | 上海联影智能医疗科技有限公司 | Training method, computer equipment and the storage medium of image segmentation |
CN110309855B (en) * | 2019-05-30 | 2021-11-23 | 上海联影智能医疗科技有限公司 | Training method for image segmentation, computer device and storage medium |
CN116486116A (en) * | 2023-06-16 | 2023-07-25 | 济宁大爱服装有限公司 | Machine vision-based method for detecting abnormality of hanging machine for clothing processing |
CN116486116B (en) * | 2023-06-16 | 2023-08-29 | 济宁大爱服装有限公司 | Machine vision-based method for detecting abnormality of hanging machine for clothing processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111062915B (en) | Real-time steel pipe defect detection method based on improved YOLOv3 model | |
CN111879241B (en) | Mobile phone battery size measuring method based on machine vision | |
CN110443836A (en) | A kind of point cloud data autoegistration method and device based on plane characteristic | |
CN107146246A (en) | One kind is used for workpiece machining surface background texture suppressing method | |
CN108389250A (en) | The method for quickly generating building cross-section diagram based on point cloud data | |
CN103292701A (en) | Machine-vision-based online dimensional measurement method of precise instrument | |
CN105447512A (en) | Coarse-fine optical surface defect detection method and coarse-fine optical surface defect detection device | |
CN113920081A (en) | Cutter wear degree detection method | |
CN107590347A (en) | One kind is based on the identification of matching isolated point and delet method and the system of designing a model | |
CN116433584A (en) | Surface defect detection method, system and storage medium for strip-shaped polishing template | |
CN116188544A (en) | Point cloud registration method combining edge features | |
CN113607058B (en) | Straight blade size detection method and system based on machine vision | |
CN106989672A (en) | A kind of workpiece measuring based on machine vision | |
CN107192348A (en) | A kind of high-precision 3D vision measuring methods | |
CN107478656A (en) | Paper pulp mixing effect method of determination and evaluation based on machine vision, device, system | |
CN116880353A (en) | Machine tool setting method based on two-point gap | |
CN103413170B (en) | For the real-time location method at paper money counter bank note edge | |
CN113450315B (en) | Bar counting method, bar counting device and steel separating system | |
CN113269743B (en) | Chip quantity detection method based on iterative translation verification | |
CN102840835A (en) | Wool diameter detecting method based on Euclidean distance and image block | |
CN112766685A (en) | Road engineering quality supervision method based on big data analysis and machine vision and cloud computing supervision platform | |
CN108279241A (en) | A kind of workpiece configurations detection method based on machine vision | |
CN111242918A (en) | Image segmentation method and system based on Kalman filtering and Markov random field | |
CN111751874B (en) | Method and device for correcting variable offset VSP post-stack variable coverage times | |
CN117094998B (en) | Defect detection method in monocrystalline silicon wafer production process |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170908 |