Rapid strip steel scratch defect detection method based on image recognition
A technology of image recognition and defect detection, which is applied to the details of image stitching, image enhancement, image analysis, etc. It can solve problems such as poor robustness, high algorithm complexity, and algorithm instability, and achieve the effect of enhancing defect characteristics
Pending Publication Date: 2021-11-09
XI'AN POLYTECHNIC UNIVERSITY
View PDF0 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to provide a fast strip steel scratch defect detection method based on image recognition, which solves the problems of excessive algorithm complexity, algorithm instability and poor robustness existing in the prior art
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0020] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0021] refer to figure 1 , the detection method of the strip steel scratch defect degree that the present invention is based on, implement according to the following steps:
[0022] Step 1, get the detection image,
[0023] Under high-brightness LED lighting conditions, industrial cameras are used to collect real-time images of the upper and lower surfaces of the strip to ensure that high-definition images of the strip surface can be obtained in harsh steel mill environments. 1 ;
[0024] Step 2, for the image I obtained in step 1 1 for preprocessing,
[0025] Using the improved mean shift smoothing algorithm to image I 1 Perform background smoothing, enhance scratch edge details, and construct a nonlinear transformation function to improve image contrast. The algorithm flow of mean shift smoothing is as follows figure 2 as shown,
[...
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 rapid strip steel scratch defect detection method based on image recognition. The method comprises the following steps: step 1, obtaining a high-definition image I1; step 2, carrying out background smoothing on the image I1 by adopting an improved mean shift smoothing algorithm, enhancing the detail part of the scratch edge, and constructing a nonlinear transformation function to improve the image contrast to obtain an image I3; step 3, carrying out blocking processing on the image I3, carrying out sub-block number sequence number marking on the sub-block image, and carrying out statistics on a gray level total number, a gray level mean value, a skewness coefficient SK and a gray level distance D of the sub-block by utilizing a gray level histogram of the sub-block image in sequence according to the sequence number; step 4, judging whether each sub-block contains a scratch defect or not, counting the sub-block images containing the defects, and splicing the sub-block images with scratches to obtain an image I4; according to the method, the problems that an existing algorithm is too high in complexity, unstable and poor in robustness are solved.
Description
technical field [0001] The invention belongs to the technical field of artificial intelligence and relates to an image recognition-based fast strip steel scratch defect detection method. Background technique [0002] With the development of science and technology, high-end industries such as automobiles, aerospace, machinery and electronics have higher and higher requirements for the surface quality of strip steel. However, the surface quality is mainly caused by product surface defects, and scratches are one of the common defects on the rolled steel surface. In the production process, the scratches on the surface of the strip are usually narrow and long along the running direction of the strip. There are usually two types, namely scratches in the high temperature zone and scratches in the normal temperature zone, and the colors caused by the two scratches are different. , the former is light blue or black, and the latter is off-white or metallic. The severity of scratches...
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
Login to View More IPC IPC(8): G06T7/00G06T5/00G06T3/40
CPCG06T7/0004G06T3/4038G06T2207/30136G06T2200/32G06T5/90G06T5/70
Inventor 黄新波孙苏珍张烨伍逸群高玉菡李博涛
Owner XI'AN POLYTECHNIC UNIVERSITY