CN116823830B - Textile appearance flatness assessment method based on multispectral image - Google Patents
Textile appearance flatness assessment method based on multispectral image Download PDFInfo
- Publication number
- CN116823830B CN116823830B CN202311095751.1A CN202311095751A CN116823830B CN 116823830 B CN116823830 B CN 116823830B CN 202311095751 A CN202311095751 A CN 202311095751A CN 116823830 B CN116823830 B CN 116823830B
- Authority
- CN
- China
- Prior art keywords
- textile
- image
- multispectral
- gabor
- samples
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000004753 textile Substances 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000001914 filtration Methods 0.000 claims description 8
- 238000002329 infrared spectrum Methods 0.000 claims description 8
- 238000001429 visible spectrum Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 3
- 239000000284 extract Substances 0.000 abstract description 3
- 239000004744 fabric Substances 0.000 description 8
- 238000011156 evaluation Methods 0.000 description 6
- 238000005406 washing Methods 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000037303 wrinkles Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000004043 dyeing Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10036—Multispectral image; Hyperspectral image
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Treatment Of Fiber Materials (AREA)
Abstract
The invention relates to a method for evaluating the appearance flatness of textiles based on multispectral images, which comprises the following steps of: collecting images; in a darkroom, utilizing an image acquisition device to acquire multispectral images at the same position of the surface of the textile to be assessed; step 2: preprocessing an image; preprocessing the acquired multispectral image; step 3: extracting Gabor characteristics; extracting features of the preprocessed multispectral image by using a Gabor function; step 4: classifying samples; firstly, selecting a plurality of textile samples with standard ratings, extracting Gabor characteristics of the textile samples, and classifying textiles to be assessed by adopting a KNN classifier based on the extracted Gabor characteristics of the textile samples with standard ratings; the method of the invention can extract Gabor characteristics without naked eyes by utilizing an image processing technology, adopts KNN classification, realizes automatic classification by an algorithm, and realizes objective automatic rating of the appearance flatness of textiles.
Description
Technical Field
The invention belongs to the technical field of detection, and relates to a textile appearance flatness assessment method based on multispectral images.
Background
Daily household washing and industrial washing and care processes perform a variety of physical actions on textile surfaces, resulting in various changes in the appearance of the surfaces, including irreversible wrinkles on the textile surfaces. Wrinkles on the textile surface can reduce its aesthetic appearance and its value in all aspects. Therefore, the textile industry has certain standards for evaluating the original flatness of the textile after washing and protecting, and the standards have important value in textile trade and textile quality control. Typically, such standards require standard washing and drying treatments to be performed on the textile, which are then evaluated for their ability to maintain their original apparent flatness. Such standards include AATCC 124, national standard GB/T13769, and the like, established by the American society of textile chemists and printing and dyeing chemists. In the above standards, the appearance flatness of the textile mainly depends on subjective evaluation of an evaluation staff, and the evaluation staff has to compare the similarity between the textile sample after standard washing and protection and standard templates of different grades under the observation environment specified by the standards to evaluate the flatness grade most suitable for the sample. Such methods rely on subjective feelings of the assessment staff, the accuracy of which is affected by subjective, objective factors of manual operation, and it is difficult to achieve information storage and reproduction. Therefore, in order to realize objective automatic grading of the appearance flatness of the textile, the research of a method for evaluating the appearance flatness of the textile has very important significance.
The existing fabric appearance flatness objective rating method mainly comprises a two-dimensional method and a three-dimensional method, wherein the two-dimensional method takes a gray level image of a sample as a processing object, and the three-dimensional method takes three-dimensional imaging of the surface of the sample as the processing object. The three-dimensional method has the advantages of visual imaging effect, small measurement environment dependence and the like, but is difficult to apply to the textile detection field in a short time due to lower operation efficiency. The current two-dimensional method mainly adopts a gray level image of a sample as a detection object, and takes the surface shadow characteristic of the gray level image as a flatness evaluation basis, so that the gray level image is closer to an object contacted by human subjective evaluation. But the gray level image in the visible light environment is the mapping of the three-dimensional characteristic of the textile surface in the two-dimensional imaging space, has larger dependence on the acquisition environment and has the defect of poor stability.
Therefore, the development of the method for evaluating the appearance flatness of the textile with little dependence on the environment and good stability has very important significance.
Disclosure of Invention
The invention aims to solve the problems in the prior art and provides a method for evaluating the appearance flatness of textiles based on multispectral images.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a method for evaluating the appearance flatness of a textile based on multispectral images comprises the following steps:
step 1: collecting images;
in a darkroom, utilizing an image acquisition device to acquire multispectral images at the same position of the surface of the textile to be assessed;
step 2: preprocessing an image;
preprocessing the acquired multispectral image;
step 3: extracting Gabor characteristics;
extracting features of the preprocessed multispectral image by using a Gabor function;
step 4: classifying samples;
firstly, selecting a plurality of textile samples with standard ratings, extracting Gabor characteristics of the textile samples, and classifying textiles to be assessed by adopting a KNN classifier based on the extracted Gabor characteristics of the textile samples with standard ratings; specifically, a plurality of textile samples and standard templates which are rated by standard are selected as training samples, the steps 1-3 are implemented to obtain the characteristics of the training samples, and then a KNN classifier is adopted to classify textiles to be evaluated;
at present, the appearance flatness of textiles is classified into 6 grades, namely SA-1, SA-2, SA-3, SA-3.5, SA-4 and SA-5. Wherein: SA-1 represents the worst maintenance of the flatness of the appearance, the most crumple of the fabric, and the degree of crumple gradually decreases with the increase of the grade value; SA-5 indicates the least creased and the flattest fabric. Each grade has standard sample, the prior art is that the standard sample is directly compared with the manual work, and the most image of which standard sample belongs to which grade; the method of the invention utilizes the image processing technology, can not use naked eyes, but extracts Gabor characteristics, simultaneously extracts characteristics of standard samples, and finally classifies the characteristics of the sample to be detected and the standard characteristics by adopting KNN, thus automatically determining which standard sample is most similar to the sample to be detected, and further realizing automatic classification by using an algorithm;
the multispectral image in the step 1 comprises a near infrared spectrum (780-1000 nm) image and a visible spectrum (400-700 nm) image.
As a preferable technical scheme:
according to the method for evaluating the appearance flatness of the textile based on the multispectral image, the image acquisition device in the step 1 comprises the black-and-white camera, the visible light source and the near infrared light source, wherein the black-and-white camera is arranged right above the textile, the irradiation directions of the visible light source and the near infrared light source are both 45 degrees with the surface of the textile (the infrared light source and the visible light source are both strip-shaped light sources, the infrared light source and the visible light source are small in size and are arranged in the same place in parallel, because the two light sources work alternately during shooting and do not work simultaneously, the angle between the two light sources is not important, and only the fixed angle of each shooting is ensured.
According to the method for evaluating the appearance flatness of the textile based on the multispectral image, the physical dimensions of the textile to be evaluated and a plurality of standard rated textile samples are 38cm multiplied by 38cm (namely, square with side length of 38 cm).
According to the textile appearance flatness assessment method based on the multispectral image, the near infrared spectrum image and the visible spectrum image acquired in the step 1 are two-dimensional images with 1024×1024 pixel sizes.
According to the textile appearance flatness assessment method based on the multispectral image, in the step 2, the image preprocessing refers to noise reduction of the acquired multispectral image by using median filtering, and the window size adopted by the median filtering is 5×5. The window size adopted by the median filtering is 5 multiplied by 5, and the noise such as imaging noise, fabric texture, fiber impurities, cloth cover pilling and the like on the surface of a sample can be eliminated by matching with the pixel size of an acquired image.
In the method for evaluating the appearance flatness of the textile based on the multispectral image, in the step 3, the complex expression of the Gabor function is as follows;
wherein (x, y) is a spatial position coordinate; mu and v are the scale and direction parameters of the Gabor filter respectively; sigma is the standard deviation of the Gaussian function and is the scale factor of the Gaussian window function of the modulated signal; gamma is the spatial aspect ratio, the value of which determines the shape of the Gabor function; f (f) μ Is the frequency of the sine-function wave,psi is phase offset (the standard term of trigonometric function refers to the horizontal offset of the function, the value range is-180 DEG to 180 DEG), j (2 pi f) μ x' +ψ) is the imaginary part of the Gabor function, j represents the imaginary number, θ υ Is the direction.
According to the textile appearance flatness assessment method based on the multispectral image, the multispectral image is subjected to Gabor filtration and then is output as follows:
O i ＝|H i (x，y)*g(μ，υ，σ)|；
wherein H is i (x, y) is a multispectral image, wherein i represents a visible spectrum image and an infrared spectrum image when 0 and 1 are taken respectively; g (μ, v, σ) is a Gabor filter, and if μ takes 5 dimensions, v takes 8 directions, γ takes 1, ψ=0, and the complex expression of the Gabor function is substituted, g (μ, v, σ) is expressed as:
where μ=0, 1, …,4, v=0, 1, …,7,
a method for evaluating the appearance flatness of textiles based on multispectral images is described above, wherein in step 4, the standard rated textile samples comprise six categories SA-1, SA-2, SA-3, SA-3.5, SA-4 and SA-5, and the number of each category is not less than 30 (each category sample is lack of representativeness if only one sample is absent, and a plurality of samples are needed because the wrinkle characteristics are locally random but have a certain rule on a macroscopic scale).
The beneficial effects are that:
(1) According to the method for evaluating the appearance flatness of the textile based on the multispectral image, disclosed by the invention, an image processing technology is utilized, gabor features are extracted, standard sample illumination features are extracted at the same time, and finally, the sample features to be tested and the standard features are classified by adopting KNN, so that the sample to be tested is automatically determined to be the most similar to the standard sample, and further, automatic classification is realized by an algorithm, and objective automatic grading of the appearance flatness of the textile is realized;
(2) The method has small dependence on environment and good stability, and the highest recognition rate (namely the accuracy rate) reaches 97.5 percent.
Drawings
FIG. 1 is a set of collected multispectral images, the left image is a textile image taken under a visible light source, and the right image is a textile image taken under a near infrared light source;
fig. 2 is a flow chart of a method for assessing the smoothness of a textile appearance based on multispectral images according to the present invention.
Detailed Description
The invention is further described below in conjunction with the detailed description. It is to be understood that these examples are illustrative of the present invention and are not intended to limit the scope of the present invention. Further, it is understood that various changes and modifications may be made by those skilled in the art after reading the teachings of the present invention, and such equivalents are intended to fall within the scope of the claims appended hereto.
The physical dimensions of the textiles to be assessed and of the several standard rated textile samples in the present invention were 38cm x 38cm.
A method for evaluating the appearance flatness of a textile based on multispectral images is shown in fig. 2, and comprises the following specific steps:
step 1: collecting images;
in a darkroom, a black-and-white camera, a visible light source and a near infrared light source are utilized, wherein the black-and-white camera is arranged right above the textile, and the irradiation directions of the visible light source and the near infrared light source are all 45 degrees with the surface of the textile; collecting near multispectral images (both infrared spectrum images and visible spectrum images are two-dimensional images with 1024 x 1024 pixel sizes) at the same position of the surface of the textile to be assessed;
step 2: preprocessing an image;
denoising the collected multispectral image by using median filtering with the window size of 5 multiplied by 5;
step 3: extracting Gabor characteristics;
and extracting characteristics of the preprocessed multispectral image by using a Gabor function, and outputting the characteristics as follows:
O i ＝|H i (x，y)*g(μ，υ，σ)|；
wherein H is i (x, y) is a multispectral image, wherein i represents a visible spectrum image and an infrared spectrum image when 0 and 1 are taken respectively; g (μ, v, σ) is a Gabor filter used, and assuming that μ takes 5 dimensions, v takes 8 directions, y takes 1, ψ=0, and the complex expression of the Gabor function is substituted, g (μ, v, σ) is expressed as:
where μ=0, 1, …,4, v=0, 1, …,7,
the complex expression of the Gabor function is as follows;
wherein (x, y) is a spatial position coordinate; mu and v are the scale and direction parameters of the Gabor filter respectively; sigma is the standard deviation of the gaussian function; gamma is the spatial aspect ratio; f (f) μ Frequency of sine function waveThe rate of the product is determined by the ratio, psi is the phase offset, j (2pi.f μ x' +ψ) is the imaginary part of the Gabor function, j represents the imaginary number, θ υ In the direction, x 'is a horizontal coordinate, and y' is a vertical coordinate;
step 4: classifying samples;
firstly, selecting a plurality of textile samples with standard ratings, extracting Gabor characteristics of the textile samples, and classifying textiles to be assessed by adopting a KNN classifier based on the extracted Gabor characteristics of the textile samples with standard ratings.
The flatness of the textile is divided into 6 classes, including SA-1, SA-2, SA-3, SA-3.5, SA-4 and SA-5, and the textile is directly realized by extracting the characteristics of a standard template and classifying the characteristics of a sample to be detected. In order to verify the effect of the invention, 198 groups of samples plus 6 groups of standard templates = 204 groups of samples are artificially manufactured, 34 groups of images are equivalent to each grade for experiment, a KNN classifier is adopted for grade classification, the accuracy of each class is counted, and then the average is carried out, so that the evaluation accuracy of the method is obtained.
According to AATCC standard fabric templates, the flatness of the fabric can be divided into 6 grades, and in order to verify the effectiveness of the method, a group of multispectral images are acquired for the AATCC standard templates of 6 different grades respectively, and the total number of the multispectral images is 6; test samples were made using standard washing procedures for the fabric swatches, 33 samples were made for each flatness grade, and 198 sets of multispectral images were collected, totaling 204 sets of samples.
The size of the Gabor filter kernel is 35 multiplied by 35, 5 scales and 8 directions are taken, 40 filters are added up, the characteristics of the textile surface image of each selected wave band are extracted, two-dimensional images with 1024 multiplied by 1024 pixel sizes are respectively obtained under a multispectral camera, and a multispectral image of a group of test samples is shown in figure 1. According to the invention, a KNN classifier is adopted to classify samples, 162 groups are selected as training sample sets during testing, the rest 42 groups are selected as test sample sets, 5 times of cross experiments are adopted for verification, the result is shown in table 1, and the highest recognition rate (namely accuracy) of the method reaches 97.5%, so that the effectiveness of the method is demonstrated.
Table 1 textile appearance flatness assessment method based on multispectral image cross-validation results
| Experiment number | 1 | 2 | 3 | 4 | 5 |
| Accuracy rate of | 97.5％ | 90.0％ | 92.5％ | 95.0％ | 97.5％ |
Claims (6)
1. A method for evaluating the appearance flatness of a textile based on multispectral images is characterized by comprising the following steps:
step 1: collecting images;
in a darkroom, utilizing an image acquisition device to acquire multispectral images at the same position of the surface of the textile to be assessed;
step 2: preprocessing an image;
preprocessing the acquired multispectral image;
step 3: extracting Gabor characteristics;
extracting features of the preprocessed multispectral image by using a Gabor function;
step 4: classifying samples;
firstly, selecting a plurality of textile samples with standard ratings, extracting Gabor characteristics of the textile samples, and classifying textiles to be assessed by adopting a KNN classifier based on the extracted Gabor characteristics of the textile samples with standard ratings;
the multispectral image in the step 1 comprises a near infrared spectrum image and a visible spectrum image;
in step 3, the complex expression of the Gabor function is as follows:
wherein (x, y) is a spatial position coordinate; mu and v are the scale and direction parameters of the Gabor filter respectively; sigma is the standard deviation of the gaussian function; gamma is the spatial aspect ratio; f (f) μ Is the frequency of the sine-function wave,psi is the phase offset, j (2pi.f μ x' +ψ) is the imaginary part of the Gabor function, j represents the imaginary number, θ υ Is the direction;
after the multispectral image is subjected to Gabor filtration, the multispectral image is output as follows:
Ο i ＝|H i (x,y)*g(μ,υ,σ)|；
wherein H is i (x, y) is a multispectral image, wherein i represents a visible spectrum image and an infrared spectrum image when 0 and 1 are taken respectively; g (μ, v, σ) is a Gabor filter, and if μ takes 5 dimensions, v takes 8 directions, γ takes 1, ψ=0, and the complex expression of the Gabor function is substituted, g (μ, v, σ) is expressed as:
where μ=0, 1, …,4, v=0, 1, …,7,
2. the method for evaluating the appearance flatness of a textile based on multispectral images according to claim 1, wherein the image acquisition device in step 1 comprises a black-and-white camera, a visible light source and a near infrared light source, the black-and-white camera is placed right above the textile, and the irradiation directions of the visible light source and the near infrared light source are both 45 degrees with the surface of the textile.
3. A method of assessing the smoothness of the appearance of a textile based on multispectral images according to claim 1, wherein the physical dimensions of the textile to be assessed and the number of standard rated samples of the textile are 38cm x 38cm.
4. A method for evaluating the flatness of a textile appearance based on multispectral images according to claim 3, wherein the near infrared spectrum image and the visible spectrum image collected in the step 1 are two-dimensional images with pixel sizes of 1024×1024.
5. The method for evaluating the flatness of a textile appearance based on multispectral images according to claim 4, wherein the image preprocessing in step 2 is to reduce noise of the multispectral images collected by using median filtering, and the median filtering adopts a window size of 5×5.
6. The method of claim 1, wherein the standard rated textile samples of step 4 include six categories of SA-1, SA-2, SA-3, SA-3.5, SA-4 and SA-5, each category having a number of not less than 30.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311095751.1A CN116823830B (en) | 2023-08-29 | 2023-08-29 | Textile appearance flatness assessment method based on multispectral image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311095751.1A CN116823830B (en) | 2023-08-29 | 2023-08-29 | Textile appearance flatness assessment method based on multispectral image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116823830A CN116823830A (en) | 2023-09-29 |
| CN116823830B true CN116823830B (en) | 2024-01-12 |
Family
ID=88114835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311095751.1A Active CN116823830B (en) | 2023-08-29 | 2023-08-29 | Textile appearance flatness assessment method based on multispectral image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116823830B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678341A (en) * | 2016-02-19 | 2016-06-15 | 天纺标检测科技有限公司 | Wool cashmere recognition algorithm based on Gabor wavelet analysis |
| CN106529544A (en) * | 2016-10-31 | 2017-03-22 | 中山大学 | Fabric flatness objective evaluation method and fabric flatness objective evaluation device based on unsupervised machine learning |
| CN108090494A (en) * | 2017-12-15 | 2018-05-29 | 东华大学 | Based on Gabor filter and support vector machines textile flaw recognition methods |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11125736B2 (en) * | 2016-07-15 | 2021-09-21 | Henkel IP & Holding GmbH | Method for ascertaining treatment parameters of a textile by means of structural information |
-
2023
- 2023-08-29 CN CN202311095751.1A patent/CN116823830B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678341A (en) * | 2016-02-19 | 2016-06-15 | 天纺标检测科技有限公司 | Wool cashmere recognition algorithm based on Gabor wavelet analysis |
| CN106529544A (en) * | 2016-10-31 | 2017-03-22 | 中山大学 | Fabric flatness objective evaluation method and fabric flatness objective evaluation device based on unsupervised machine learning |
| CN108090494A (en) * | 2017-12-15 | 2018-05-29 | 东华大学 | Based on Gabor filter and support vector machines textile flaw recognition methods |
Non-Patent Citations (1)
| Title |
|---|
| 基于图像频域分析的织物平整度等级客观评价;石康君;中国优秀硕士学位论文全文数据库工程科技Ⅰ辑(月刊)(第01期);正文第8-12、17-22、26-38页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116823830A (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105956582B (en) | A kind of face identification system based on three-dimensional data | |
| CN112597812B (en) | A finger vein recognition method and system based on convolutional neural network and SIFT algorithm | |
| CN103324944B (en) | A False Fingerprint Detection Method Based on SVM and Sparse Representation | |
| CN105678788B (en) | A kind of fabric defect detection method based on HOG and low-rank decomposition | |
| CN101866427A (en) | Fabric defect detection and classification method | |
| CN113554080A (en) | Non-woven fabric defect detection and classification method and system based on machine vision | |
| CN108090494B (en) | Textile defect recognition method based on Gabor filter and support vector machine | |
| CN105447441A (en) | Face authentication method and device | |
| CN109801286B (en) | Surface defect detection method for LCD light guide plate | |
| CN105740829A (en) | Scanning line processing based automatic reading method for pointer instrument | |
| CN101999900A (en) | Living body detecting method and system applied to human face recognition | |
| CN110889837A (en) | A cloth defect detection method with defect classification function | |
| CN105718889A (en) | Face recognition method based on GB(2D)2PCANet deep convolution model | |
| CN103942540A (en) | False fingerprint detection algorithm based on curvelet texture analysis and SVM-KNN classification | |
| CN109118471A (en) | A kind of polishing workpiece, defect detection method suitable under complex environment | |
| CN105844278A (en) | Multi-feature fused fabric scanning pattern recognition method | |
| CN110232390B (en) | A method of image feature extraction under changing illumination | |
| CN110415222A (en) | A method for identifying side defects of silk cake based on texture features | |
| Abdullah et al. | A framework for crack detection of fresh poultry eggs at visible radiation | |
| Dixit et al. | Image texture analysis-survey | |
| CN105184777A (en) | Painted design fabric defect detection method based on image decomposition | |
| CN110348289A (en) | A kind of finger vein identification method based on binary map | |
| CN116188786B (en) | Image segmentation system for hepatic duct and biliary tract calculus | |
| CN108921006B (en) | A method for establishing the authenticity identification model of a handwritten signature image and a method for authenticating it | |
| Wankhede et al. | A low cost surface strain measurement system using image processing for sheet metal forming applications |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |