Paper defect identification and classification method based on machine vision

Abstract

The invention discloses an online paper defect identification and classification method based on machine vision. The method is implemented according to the following steps: firstly, acquiring a paperdefect image by virtue of a Spyde3 linear array CCD camera, generating data structure data from data transmitted by the CCD camera by virtue of a serialization technology, and converting the data structure data into a grayscale image for subsequent processing; and then, quickly judging whether the frame image of the image contains paper defects in real time by adopting a subtraction technology inimage template processing; and finally, carrying out feature extraction on the paper with the paper defects, and carrying out paper defect classification by adopting a machine learning classifier. Theonline paper defect identification and classification method solves the problem of insufficient memory caused by transmission of a large number of high-resolution images, realizes real-time detectionduring high-speed operation of the paper machine and final paper defect classification, and has the characteristics of high paper defect transmission rate, good detection real-time performance, accurate classification and the like.

Description

technical field [0001] The invention belongs to the field of computer image processing and automatic control, and in particular relates to a method for identifying and classifying paper defects based on machine vision. Background technique [0002] The modern papermaking industry is a technology-, capital-, resource- and energy-intensive industry. Papermaking technology is developing in the direction of large-scale equipment, automation, high efficiency, and low energy consumption. Improving paper quality is one of the important directions of independent research and development of my country's paper industry technology. In the paper industry, paper defects that do not meet the technical requirements for paper quality are called paper defects. Some paper defects are brought in from the paper material before papermaking, some are caused by poor technical operation or poor technology during papermaking, and some are caused by poor environmental sanitation in the factory. Onc...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide an online paper defect recognition and classification method based on machine vision, which solves the problem of insufficient memory caused by the transmission of a large number of high-resolution images and the inability to detect real-time problems when the paper machine is running at high speed

Images