Printing apparent defect detection method based on image similarity comparison
A defect detection and similarity technology, applied in image enhancement, image analysis, image data processing, etc., can solve problems such as manual extraction, and achieve the effect of improving efficiency
Active Publication Date: 2021-06-01
XIAN UNIV OF TECH
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The purpose of the present invention is to provide a printing apparent defect detection method based on image similarity comparison, which solves the problem of manually extracting defect features in the prior art question
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
[0031] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0032] A printing apparent defect detection method based on image similarity comparison, such as figure 1 shown, including the following steps:
[0033] Step 1. Obtain the defective image set and the corresponding original printing image set, segment each defective image in the defective image set according to 100*100 pixels, obtain n defective image segmentation blocks, and segment the original printing image in the original printing image set , to obtain n original printed image segmentation blocks; the area at the edge of the image that cannot meet the size of 100*100 pixels is operated by filling in the blank, and the pixel value of the blank area is 255;
[0034] In this embodiment, the defect image set is automatically generated through random parameter changes, and the defect information and printed images are superimposed, a total of...
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 printing apparent defect detection method based on image similarity comparison, and the method comprises the steps: carrying out the segmentation of each defect image and a corresponding printing original image, and obtaining defect image segmentation blocks and printing original image segmentation blocks; inputting the defect image segmentation blocks and the printing original image segmentation blocks into a similarity detection network for feature extraction and normalization operation; screening the defect image segmentation blocks according to a normalization operation result, and conveying the screened defect image segmentation blocks to a feature extraction network for feature extraction to obtain features of three different scales; performing feature fusion on two of the features, and transmitting the third feature to a feature pyramid pooling network to respectively obtain three prediction features; decoding the three prediction features to obtain three printed matter defect prediction frames, and screening the three printed matter defect prediction frames to obtain a defect boundary frame. Defect features do not need to be manually extracted, and the efficiency of printing apparent defect detection tasks can be improved.
Description
technical field [0001] The invention belongs to the technical field of image detection and relates to a method for detecting printing apparent defects based on image similarity comparison. Background technique [0002] With the development of the times and the changes of society, the rapid development of network technology and communication technology is followed by the continuous development and changes of digital image technology. As one of the most direct and important carriers of information, digital images are also an indispensable part of people's lives today. On the one hand, with the continuous improvement of hardware facilities such as industrial cameras, the way people acquire and process images has become increasingly simple. On the other hand, with the adjustment of my country's industrial structure and the improvement of economic level, the requirements for the appearance, design and color of packaging such as gifts, medicines, and luxury goods have been greatl...
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 Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T7/11G06T7/62G06K9/46G06K9/62
CPCG06T7/001G06T7/11G06T7/62G06T2207/10004G06T2207/30144G06T2207/20084G06T2207/20081G06V10/44G06V10/462G06F18/22Y02P90/30
Inventor 郑元林楼豪杰廖开阳李佳陈兵董素馨宋天泽谢雨林张新会
Owner XIAN UNIV OF TECH