CN110570404A - Sobel operator-based cloth defect detection method - Google Patents
Sobel operator-based cloth defect detection method Download PDFInfo
- Publication number
- CN110570404A CN110570404A CN201910789108.6A CN201910789108A CN110570404A CN 110570404 A CN110570404 A CN 110570404A CN 201910789108 A CN201910789108 A CN 201910789108A CN 110570404 A CN110570404 A CN 110570404A
- Authority
- CN
- China
- Prior art keywords
- image
- block
- image block
- sobel operator
- pixel values
- 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 63
- 230000007547 defect Effects 0.000 title claims abstract description 58
- 239000004744 fabric Substances 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000001914 filtration Methods 0.000 claims abstract description 6
- 238000003708 edge detection Methods 0.000 claims abstract description 4
- 238000000638 solvent extraction Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000005065 mining Methods 0.000 claims description 6
- 230000002194 synthesizing effect Effects 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000000903 blocking effect Effects 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 3
- 239000002131 composite material Substances 0.000 abstract 2
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000001228 spectrum Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000004753 textile Substances 0.000 description 1
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
- G06T7/0012—Biomedical 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
- G06T7/11—Region-based segmentation
-
- 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
- G06T7/10—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
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- 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
- G06T2207/30124—Fabrics; Textile; Paper
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
the invention discloses a defect detection method based on a Sobel operator, and belongs to the field of image detection. Firstly, Sobel operator filtering is carried out on an image to obtain a preliminary binaryzation defect image, then, the preliminary defect detection image is partitioned, the number of nonzero pixel values in each image block is counted, the image blocks are partitioned into image blocks containing defects and image blocks not containing defects by combining a threshold value, and finally, the image blocks are synthesized into the defect image. To further suppress noise, the composite image block is subjected to a loop process of further blocking the composite image block by a threshold value. The invention establishes a new Sobel-IP defect detection method by combining a Sobel operator with image blocking. The edge detection effect of the Sobel operator is fully utilized, after an initial detection result is obtained, secondary blocking threshold processing is carried out on the image, defects in the cloth can be accurately detected, noise can be effectively suppressed, the cloth defect detection efficiency is improved, and the false detection rate is reduced.
Description
Technical Field
The invention belongs to the technical field of image detection, and particularly relates to a cloth defect detection method based on a Sobel operator.
background
Cloth defect detection is a key step in ensuring the quality of cloth, and therefore has been a popular topic in the textile industry. The traditional detection of cloth mainly relies on people's vision to accomplish, and this kind of detection mode is not only inefficiency, and it is very high to detect the error rate moreover. There are studies showing that: even professional inspectors can only achieve the cloth inspection rate of about 70 percent [1 ]. In recent years, computer vision-based detection methods are adopted to make up for the defects of the traditional cloth defect detection, and the core of the methods is to design a quick and effective algorithm.
The existing defect detection methods are mainly divided into three categories: statistical-based methods, spectral methods, and model-based methods.
a typical gray level co-occurrence matrix method [2] is compared based on a statistical method, a spectrum method uses the spectrum characteristics of an image for defect detection, and the spectrum method mainly comprises Fourier transform [3] and wavelet transform [4 ]. The model-based method mainly starts from the structure of data, and typically comprises an autoregressive model [5] and a Markov random model [6 ].
The defects existing in the defect detection at present mainly comprise: (1) due to various reasons such as picture acquisition and the like, noise introduction is inevitable, so that the false detection rate of the common detection method is too high; (2) the partial defect detection method has the defects that the real-time detection is difficult to realize due to the complexity of the algorithm while the higher detection rate is obtained.
[1]H.Sari-Sarraf,JS.Goddard,Vision systems for on-loom fabric inspection.IEEE Trans.Ind.Appl,35(6),1252-1259(1999).
[2]A.Latif-Amet,A.Ertuzun,A.Ercil,An efficient method for texture defect detection:sub-band domain co-occurrence matrices,Image and VisionComputing 18,543–55(2000).
[3]CH.Chan,G.Pang,Fabric defect detection by Fourier analysis,IEEE Trans.Ind.Appl.36(5),1743-1750(2000).
[4]Y.Han,P.Shi,An adaptive level-selecting wavelet transform for texture defect detection,Image Vision Comput,25(8),1239-1248(2007).
[5]J.Zhou,D.Semenovich,A.Sowmya,J.Wang,Dictionary learning framework for fabric defect detection,The Journal of the Textile Institute,105(3),223-234(2014).
[6]S.Ozdemir,A.Ercil,Markov random fields and Karhunen-Loeve transform for defect inspection of textile products.IEEE Conference onEmerging Technologies&Factory Automation,1996,pp.697-703.
Disclosure of Invention
The purpose of the invention is as follows: the invention provides a cloth defect detection method based on Sobel operator, which aims at the problems that the false detection rate of the current cloth defect detection method is too high, and the real-time detection is difficult to realize when the partial defect detection method obtains higher detection rate. The method is based on Sobel operator combined with image block statistics, can effectively detect defects and inhibit noise, and can be applied to a real-time image processing system.
the technical scheme is as follows: in order to realize the purpose of the invention, the technical scheme adopted by the invention is as follows: a cloth defect detection method based on a Sobel operator comprises the following steps:
Step 1: carrying out Sobel operator filtering on the collected cloth defect image to obtain an initial estimation image;
step 2: partitioning the estimated image, and counting the number of non-zero pixel values in each image block to obtain a statistical result of the pixel values in each image block;
And step 3: setting a threshold value, and performing binarization processing on a statistical result of pixel values in an image block to obtain an image block after binarization processing;
And 4, step 4: synthesizing the image blocks after binarization processing to obtain a secondary estimation image;
and 5: repeating the steps 2 to 4 on the secondary estimation image obtained in the step 4 to obtain a final detection imageImplementing Sobel operator andAnd (5) carrying out image blocking statistical detection.
Further, the step 1 performs Sobel operator filtering on the acquired image to obtain an initial estimation image; the method comprises the following steps:
1-1, detecting the edges of the acquired cloth defect images y by using a Sobel operator, wherein the Sobel operator comprises two convolution kernels, namely a transverse convolution kernel and a longitudinal convolution kernel, and performing convolution operation on the transverse convolution kernel and the longitudinal convolution kernel and the defect images y respectively to obtain the cloth defect images y
Wherein is the convolution operator, Gxand GyRepresenting the image gradient values of the lateral and longitudinal edge detection, respectively;
1-2, after all pixels of the image are operated by a convolution operator, calculating the gradient size of the corresponding pixel according to the transverse and longitudinal gradient values of each pixel of the image, thereby obtaining a gradient image; the gradient magnitude calculation is as follows:
wherein G represents the gradient of the pixel point;
And 1-3, carrying out binarization operation on the gradient image obtained in the step 1-2 to obtain a binarized image, and recording the binarized image as x, wherein the binarized image is an initial estimation image.
Further, the step 2 is to block the estimated image, and count the number of non-zero pixel values in each image block to obtain a statistical result of the pixel values in each image block; the method comprises the following steps:
partitioning the image x according to a matrix block mining operator to obtain an image block xiexpressed as follows:
xi＝Rix i＝1,2,...,n
wherein R isifor the matrix block mining operator, n represents the number of image blocks, the scale of the blocks is m × m, there are 2 images between blocksThe prime values overlap; preferably, the block size is 7 × 7, which is the best detection result;
and after the image x is partitioned, counting the number of non-zero pixel values in each image block to obtain a statistical result of each image block.
Further, setting a threshold value in the step 3, and performing binarization processing on a statistical result of pixel values in the image block to obtain a binarized image block; the method comprises the following specific steps:
judging whether the number of the non-zero pixel values in each image block obtained in the step (2) meets a threshold condition or not;
if the number of the non-zero pixel values in the image block is larger than a set threshold, the image block contains defects, and the pixel values in the image block are kept unchanged; otherwise, the image block only contains noise points, the pixel value of the whole image block is set to be 0, and a binary image block is obtained
further, the image blocks after the binarization processing are synthesized in the step 4 to obtain a secondary estimation image; the method comprises the following steps: after all the binarized image blocks are obtained, the imageObtained by solving the following minimization problem:
The above formula is solved into
Will estimate the image blockPlacing the image at the corresponding position of the original image y, and averaging the pixel values at the overlapped pixel part to obtain a detection image
Further, the image obtained in step 4 is utilizedalthough part of the noise is suppressed, the noise is still present at this time. Due to the block-to-block overlap during defect detection, the noise becomes more and more sparse. To further reduce the false detection rate, the detection image is processedpartitioning is carried out again, the number of non-zero pixel values in each block is counted, and a final detection image is obtainedthrough twice circulation, the noise can be effectively reduced, and simultaneously the defects can be completely detected.
has the advantages that: compared with the prior art, the technical scheme of the invention has the following beneficial technical effects:
the invention mainly solves the problem of cloth defect detection, establishes a new Sobel-IP defect detection method by combining an Image Patch (IP) statistical strategy through a Sobel operator, and finally realizes the aim of cloth intelligent detection. Compared with the existing defect detection algorithm, the Sobel-IP defect detection algorithm utilizes a Sobel operator to detect defect images, then blocks the images and carries out threshold processing, so that the real-time performance of the algorithm can be maintained in the detection, and meanwhile, the detection efficiency can be effectively improved. Due to the adoption of the secondary circulation algorithm, the noise can be effectively inhibited, and the purpose of reducing the false detection rate is achieved.
Drawings
FIG. 1 is a flow chart of image defect detection in accordance with the present invention;
FIG. 2 is an illustration of a sample of the present invention.
Detailed Description
the technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
the invention discloses a cloth defect detection method based on a Sobel operator, which has a detection flow shown in figure 1 and comprises the following steps:
step 1: performing Sobel operator filtering on the cloth defect image acquired by the industrial camera to obtain an initial estimation image; the method comprises the following specific steps:
1-1, detecting the edges of the acquired cloth defect image y by using a Sobel operator, wherein the Sobel operator comprises two convolution kernels, namely a transverse convolution kernel and a longitudinal convolution kernel; respectively carrying out convolution operation on the transverse convolution kernel and the longitudinal convolution kernel and the defect image y to obtain
Wherein is the convolution operator, GxAnd GyRepresenting the image gradient values of the lateral and longitudinal edge detection, respectively;
1-2, after all pixels of the image are operated by a convolution operator, calculating the gradient size of the corresponding pixel according to the transverse and longitudinal gradient values of each pixel of the image, thereby obtaining a gradient image; the gradient magnitude calculation is as follows:
And 1-3, carrying out binarization operation on the gradient image obtained in the step 1-2 to obtain a binarized image, and recording the binarized image as x, wherein the binarized image is an initial estimation image.
Step 2: partitioning the estimated image, and counting the number of non-zero pixel values in each image block to obtain a statistical result of the pixel values in each image block; the method comprises the following specific steps:
partitioning the image x according to a matrix block mining operator to obtain an image block xiExpressed as follows:
xi＝Rix i＝1,2,...,n
Wherein R isiFor the matrix block mining operator, n denotes the number of image blocks, the scale of the blocks is 7 x 7,There is 2 pixel value overlap between blocks;
and after the image x is partitioned, counting the number of non-zero pixel values in each image block to obtain a statistical result of each image block.
And step 3: setting a threshold value, and performing binarization processing on a statistical result of pixel values in an image block to obtain an image block after binarization processing; the method comprises the following specific steps:
Judging whether the number of the non-zero pixel values in each image block obtained in the step (2) meets a threshold condition or not;
If the number of the non-zero pixel values in the image block is larger than a set threshold, the image block contains defects, and the pixel values in the image block are kept unchanged; otherwise, the image block only contains noise points, the pixel value of the whole image block is set to be 0, and a binary image block is obtained
and 4, step 4: synthesizing the image blocks after binarization processing to obtain a secondary estimation image; the method comprises the following steps:
After all the binarized image blocks are obtained, the imageObtained by solving the following minimization problem:
the above formula is solved into
will estimate the image blockPlacing the image at the corresponding position of the original image y, and averaging the pixel values at the overlapped pixel part to obtain a detection image
And 5: repeating the steps 2 to 4 on the secondary estimation image obtained in the step 4 to obtain a final detection imageand realizing Sobel operator and image block statistical detection.
Using the image obtained in step 4Although part of the noise is suppressed, the noise is still present at this time. Due to the block-to-block overlap during defect detection, the noise becomes more and more sparse. To further reduce the false detection rate, the detection image is processedPartitioning is carried out again, the number of non-zero pixel values in each block is counted, and a final detection image is obtainedThrough the two-step circulation, the noise can be effectively reduced, and simultaneously the defects can be completely detected.
In the embodiment, the detection method of the sobel operator and the image block statistics is used for the defect picture test, and the result shows that the method not only effectively improves the defect detection efficiency, but also reduces the false detection rate and obtains better detection performance.
Some specific detection examples are given below. As shown in fig. 2, fig. 2(a), 2(b) and 2(c) are defect images, and fig. 2(d), 2(e) and 2(f) are cloth defect detection effect graphs based on Sobel operator combined image blocking statistics according to this embodiment.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and all simple modifications and equivalent variations of the above embodiment according to the technical spirit of the present invention are included in the protection scope of the present invention.
Claims (5)
1. a cloth defect detection method based on a Sobel operator is characterized by comprising the following steps: the method comprises the following steps:
step 1: carrying out Sobel operator filtering on the collected cloth defect image to obtain an initial estimation image;
Step 2: partitioning the estimated image, and counting the number of non-zero pixel values in each image block to obtain a statistical result of the pixel values in each image block;
And step 3: setting a threshold value, and performing binarization processing on a statistical result of pixel values in an image block to obtain an image block after binarization processing;
and 4, step 4: synthesizing the image blocks after binarization processing to obtain a secondary estimation image;
And 5: and (4) repeating the steps 2 to 4 on the secondary estimation image obtained in the step 4 to obtain a final detection image, and realizing the block statistical detection of the Sobel operator and the image.
2. the Sobel operator-based cloth defect detection method according to claim 1, further comprising: step 1, Sobel operator filtering is carried out on the cloth defect image to obtain an initial estimation image; the method comprises the following steps:
1-1, detecting the edges of the acquired cloth defect images y by using a Sobel operator, wherein the Sobel operator comprises two convolution kernels, namely a transverse convolution kernel and a longitudinal convolution kernel, and performing convolution operation on the transverse convolution kernel and the longitudinal convolution kernel and the defect images y respectively to obtain the cloth defect images y
wherein is the convolution operator, GxAnd GyRepresenting the image gradient values of the lateral and longitudinal edge detection, respectively;
1-2, after all pixels of the image are operated by a convolution operator, calculating the gradient size of the corresponding pixel according to the transverse and longitudinal gradient values of each pixel of the image, thereby obtaining a gradient image; the gradient magnitude calculation is as follows:
wherein G represents the gradient of the pixel point;
And 1-3, carrying out binarization operation on the gradient image obtained in the step 1-2 to obtain a binarized image, and recording the binarized image as x, wherein the binarized image is an initial estimation image.
3. the Sobel operator-based cloth defect detection method according to claim 2, wherein: the step 2 is to divide the estimated image into blocks and count the number of non-zero pixel values in each image block to obtain the statistical result of the pixel values in each image block; the method comprises the following steps:
Partitioning the image x according to a matrix block mining operator to obtain an image block xiExpressed as follows:
xi＝Rix i＝1,2,...,n
Wherein R isimining operators for matrix blocks, wherein n represents the number of image blocks, the scale of each block is m multiplied by m, and 2 pixel values are overlapped among the blocks;
And after the image x is partitioned, counting the number of non-zero pixel values in each image block to obtain a statistical result of each image block.
4. The Sobel operator-based cloth defect detection method according to claim 3, wherein: setting a threshold value, and performing binarization processing on a statistical result of pixel values in the image block to obtain an image block after binarization processing; the method comprises the following specific steps:
judging whether the number of the non-zero pixel values in each image block obtained in the step (2) meets a threshold condition or not;
If the number of the non-zero pixel values in the image block is larger than a set threshold, the image block contains defects, and the pixel values in the image block are kept unchanged; otherwise, the image block only contains noise points, the pixel value of the whole image block is set to be 0, and binarization is obtainedImage block of
5. the Sobel operator-based cloth defect detection method according to claim 4, wherein: step 4, synthesizing the image blocks after binarization processing to obtain a secondary estimation image; the method comprises the following steps:
After all the binarized image blocks are obtained, the imageobtained by solving the following minimization problem:
The above formula is solved into
will estimate the image blockPlacing the image at the corresponding position of the original image y, and averaging the pixel values at the overlapped pixel part to obtain a detection image
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910789108.6A CN110570404A (en) | 2019-08-26 | 2019-08-26 | Sobel operator-based cloth defect detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910789108.6A CN110570404A (en) | 2019-08-26 | 2019-08-26 | Sobel operator-based cloth defect detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110570404A true CN110570404A (en) | 2019-12-13 |
Family
ID=68776244
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910789108.6A Pending CN110570404A (en) | 2019-08-26 | 2019-08-26 | Sobel operator-based cloth defect detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110570404A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111768376A (en) * | 2020-06-24 | 2020-10-13 | 山东科技大学 | Eddy current thermal imaging edge detection method and system, storage medium and application |
| CN112365448A (en) * | 2020-10-20 | 2021-02-12 | 天津大学 | Fabric defect detection method in warp knitting process |
| CN112435232A (en) * | 2020-11-23 | 2021-03-02 | 南京信息工程大学 | Defect detection method based on haar wavelet combined image variance |
| CN114882034A (en) * | 2022-07-11 | 2022-08-09 | 南通世森布业有限公司 | Fabric dyeing quality evaluation method based on image processing |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678788A (en) * | 2016-02-19 | 2016-06-15 | 中原工学院 | Fabric defect detection method based on HOG and low-rank decomposition |
| CN110084246A (en) * | 2019-04-17 | 2019-08-02 | 江南大学 | A kind of yarn dyed fabric fault automatic identifying method |
-
2019
- 2019-08-26 CN CN201910789108.6A patent/CN110570404A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678788A (en) * | 2016-02-19 | 2016-06-15 | 中原工学院 | Fabric defect detection method based on HOG and low-rank decomposition |
| CN110084246A (en) * | 2019-04-17 | 2019-08-02 | 江南大学 | A kind of yarn dyed fabric fault automatic identifying method |
Non-Patent Citations (3)
| Title |
|---|
| LE TONG等: "Fabric Defect Detection for Apparel Industry：A Nonlocal Sparse Representation Approach", 《IEEE ACCESS》 * |
| 唐旭晟等: "基于Gabor滤波器对织造前帘子布疵点检测研究", 《机电工程》 * |
| 肖俊明等: "边缘检测算子在帘子布疵点检测应用中的研究", 《现代计算机》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111768376A (en) * | 2020-06-24 | 2020-10-13 | 山东科技大学 | Eddy current thermal imaging edge detection method and system, storage medium and application |
| CN112365448A (en) * | 2020-10-20 | 2021-02-12 | 天津大学 | Fabric defect detection method in warp knitting process |
| CN112365448B (en) * | 2020-10-20 | 2022-08-30 | 天津大学 | Method for detecting fabric defects in warp knitting process |
| CN112435232A (en) * | 2020-11-23 | 2021-03-02 | 南京信息工程大学 | Defect detection method based on haar wavelet combined image variance |
| CN114882034A (en) * | 2022-07-11 | 2022-08-09 | 南通世森布业有限公司 | Fabric dyeing quality evaluation method based on image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110570404A (en) | Sobel operator-based cloth defect detection method | |
| US20220020134A1 (en) | Method and system for quickly matching image features applied to mine machine vision | |
| CN108921800B (en) | Non-local mean denoising method based on shape self-adaptive search window | |
| CN102368821B (en) | Adaptive noise intensity video denoising method and system thereof | |
| CN108052980B (en) | Image-based air quality grade detection method | |
| CN111260616A (en) | Insulator crack detection method based on Canny operator two-dimensional threshold segmentation optimization | |
| CN109064418B (en) | Non-local mean value-based non-uniform noise image denoising method | |
| CN107360435B (en) | Blockiness detection methods, block noise filtering method and device | |
| CN105701477B (en) | A kind of fabric defect detection method based on Stationary Wavelet Transform vision significance | |
| CN108932699B (en) | Three-dimensional matching harmonic filtering image denoising method based on transform domain | |
| CN108510496B (en) | Fuzzy detection method for SVD (singular value decomposition) based on image DCT (discrete cosine transformation) domain | |
| WO2022143421A1 (en) | Noise intensity estimation method and apparatus, and electronic device | |
| CN110351453A (en) | A kind of computer video data processing method | |
| CN102118547A (en) | Image weighted filtering method | |
| CN106203536B (en) | Feature extraction and detection method for fabric defects | |
| CN115511907A (en) | Scratch detection method for LED screen | |
| CN106254723B (en) | A kind of method of real-time monitoring video noise interference | |
| Zhao et al. | Analysis of image edge checking algorithms for the estimation of pear size | |
| CN110111355B (en) | Moving vehicle tracking method capable of resisting strong shadow interference | |
| CN107798676B (en) | No-reference image quality perception method established based on multi-scale natural scene statistics | |
| CN114693543B (en) | Image noise reduction method and device, image processing chip and image acquisition equipment | |
| CN112767261B (en) | Non-local denoising frame for color image and video based on generalized non-convex tensor robust principal component analysis model | |
| CN112651936B (en) | Steel plate surface defect image segmentation method and system based on image local entropy | |
| CN108198140A (en) | Three-dimensional collaboration filtering and noise reduction method based on NCSR models | |
| Bhateja et al. | A reduced reference distortion estimation measure for color images |
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: 20191213 |