Coating defect detection system based on deep learning

Abstract

The invention relates to a coating defect detection system based on deep learning, and the system comprises an image collection module which is used for obtaining various types of melt-blown fabric gluing surface images of a coating production line; the image processing module is connected with the image acquisition module and is used for carrying out preprocessing and feature extraction on the image acquired by the camera; the image processing module comprises an image preprocessing module and an image feature extraction module; and the image preprocessing module is used for uniformly segmenting the acquired image into a plurality of small images with set sizes, and the image analysis module is connected with the image processing module and used for judging whether the image has defects or not. Through cooperation of the image acquisition module, the image processing module and the image analysis module, detection of different types of melt-blown fabric gluing surface defects can be efficiently realized, and the method is high in detection precision, wide in adaptability and high in speed.

Description

technical field [0001] The invention relates to the technical fields of machine vision and image processing, in particular to a coating defect detection system based on deep learning. Background technique [0002] Coating is widely used in the surface processing of various membranes, paper, non-woven fabrics and other materials, and is one of the key links in the process of producing nanofiltration membranes and reverse osmosis membranes. In the coating industrial production, due to various factors, the coated melt-blown cloth will have defects such as scratches, vertical lines, bright spots and wrinkles. The existence of these defects leads to a decrease in the yield of the product. [0003] In the production process of domestic coating technology, large companies all use imported equipment to monitor the change of coating thickness, which is expensive. Other small entrepreneurial companies mostly stay in the traditional manual visual inspection stage. The characteristic...

AI Technical Summary

Problems solved by technology

The characteristics of traditional manual inspection do not require professional equipment and only need to guide and train professionals, but its disadvantage is that the results are greatly affected by subjective factors, which will lead to missed inspections and false inspections, and the defects can only be sampled offline after coating is completed. , unable to detect online in real time

Images