Cloth defect detection method and device based on machine learning
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of machine learning and cloth detection, applied in the direction of neural learning methods, instruments, computer components, etc., can solve the problems of high missed detection rate, high false detection rate, and difficulty in meeting industrial needs, so as to achieve a high degree of automation and liberate productivity Effect
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0004] The Chinese patent with the application number: 201410467132.5 discloses the "machine vision-based automatic detection and recognition device and method for cloth defects", although the device and method overcome the traditional artificial vision detection speed, low precision, high missed detection rate, and high false detection rate defects, but it does not have self-learning performance, with the development of industry, it will be difficult to meet higher industrial needs
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0044] Embodiment 1: A method for detecting cloth defects based on machine learning.
[0045] refer to Figure 1 to Figure 5 As shown in any one, a method for detecting cloth defects based on machine learning specifically includes the following steps:
[0046] Step 1: Image segmentation, in order to facilitate subsequent processing, the collected image is uniformly divided into 256*256 sub-images;
[0047] Step 2: image preprocessing; the step 2 is specifically as follows:
[0048] Step 21: image enhancement, extraction of effective regions;
[0049] Step 22: Image denoising, using a Gaussian filter to remove noise;
[0050] Step 23: Segment the defect area, segment the cloth defect area from the whole image.
[0051] Step 3: sub-image feature extraction, using an image processing method based on Gabor wavelet transform and projection method to extract the feature parameters of the sub-image;
[0052] Step 4: Cloth defect detection; the step 4 is specifically as follows:
...
Embodiment 2
[0064] Embodiment 2: A cloth defect detection device based on machine learning.
[0065] refer to Figure 5 As shown, a detection device based on the machine learning-based cloth defect detection method in Embodiment 1 includes:
[0066] Image acquisition unit 1, described image acquisition unit 1 comprises infrared light source 101 and industrial camera 102, image processing unit 2, described image processing unit 2 comprises industrial computer 201, data communication unit 3, and described data communication unit 3 comprises host computer 301 and the lower computer 302, the action execution unit 4, the action execution unit 4 includes an encoder 401 and a marking machine 402, the encoder 401 detects the speed signal of the moving cloth, and this signal is fed back to the conveyor belt motor, so that the cloth speed and the camera The shooting speed is the same; the upper computer 301 sends the position and type of the detected cloth defect to the lower computer 302, and the...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention discloses a cloth defect detection method based on machine learning. The method particularly comprises the following steps of image segmentation, image enhancement, image denoising, sub image feature extraction, defect point area segmentation, offline cloth learning, online cloth detection, and cloth defect point classification. In the offline cloth learning stage, a BP neural network is used to train standard image characteristic parameters, and a standard value is obtained. In the online cloth detection stage, the BP neural network is used to detect the feature parameters of the sub image. In the cloth defect point classification stage, a depth learning algorithm based on a convolutional neural network is used to classify cloth defects. The cloth defect detection method based on machine learning has a self-learning function and can meet the continuously-developing industry needs. The invention also provides a cloth defect detection device based on machine learning, which comprises an image acquisition unit, an image processing unit, a data communication unit and an action execution unit. The detection device can realize high-efficiency and accurate detection, and workers can be freed from heavy and tasteless physical labor.
Description
technical field [0001] The invention relates to the field of cloth detection, in particular to a method and device for detecting cloth defects based on machine learning. Background technique [0002] Textile industry is the pillar industry of my country's national economy. Textile industry, together with steel, automobile, shipbuilding, petrochemical, light industry, non-ferrous metal, equipment manufacturing, electronic information and logistics industries, is the main industry composition of my country. In the process of textile production, surface defects of cloth are the key factors affecting the quality of cloth. Cloth surface defects directly affect the grading of cloth. The price of second-class products is only 45%-65% of first-class products. Fabric defects seriously affect the economic income of the textile industry. Therefore, cloth defect detection is particularly important in textile quality control. [0003] For a long time, cloth inspection is generally done...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more