System for detecting defects of filter paper based on machine vision technology and detection method thereof

Abstract

The invention relates to a system for detecting defects of filter paper based on a machine vision technology and a detection method thereof. The system comprises a machine frame, a machine vision device, an industrial personal computer and defect mark printers, wherein the machine vision device comprises a light source and a plurality of high-speed cameras; the industrial personal computer comprises a central microprocessor and a display of built-in embedded image processing software; the defect mark printer comprises an encoder and a plurality of defect mark printers; according to characteristics of a product to be detected, noises are eliminated through smoothing filtering by using a two-dimensional zero-mean discrete Gaussian function, and based on a roof edge subpixel positioning algorithm, the defects of the image of the product are recognized; the characteristics of materials to be detected are picked up by the high-speed cameras; and the defect mark printers are controlled by the central microprocessor. By the system and the detection method, the defects of the filter paper can be detected stably, accurately and efficiently online in real time; coordinates are automatically positioned to print defect marks; and the system can alarm automatically and display detection results in real time.

Description

[0001] technical field [0002] The invention relates to a filter paper defect detection system and a detection method based on machine vision technology, which are used for online detection and processing of filter paper defects. [0003] Background technique [0004] Cotton fiber filter paper is often used as the main material of the filter element and is a key component of the filter. There are countless small holes on the surface of this filter paper for liquid particles or gaseous particles to pass through, but relatively large solid particles cannot pass through. This property of filter paper is applied to the separation of liquid and solid substances mixed together and the separation of gaseous and solid substances mixed together, so the quality of filter paper directly affects the quality of the filter. For the defects of filter paper materials, such as through holes, thin areas (non-transparent, but of abnormal thickness), rotten edges, stains, cracks, color diffe...

AI Technical Summary

Problems solved by technology

For the defects of filter paper materials, such as through holes, thin areas (non-transparent, but of abnormal thickness), rotten edges, stains, cracks, color differences, missing, drawing, twill, holes, etc., the human eye judgment method is basically used , or unable to judge, do not use inspection methods or exempt from inspection, etc.

Obviously, the human eye judgment has shortcomings such as accuracy, low efficiency, and high missed detection rate.

[0005] Most defect detection systems in the prior art use silicon photocells to detect optical signals, which have the disadvantages of low resolution and poor ability to identify defects with smaller apertures

At the same time, its optical system has poor imaging quality, the optical path cannot be adjusted, and the imaging consistency is poor

In addition, the use of silicon photocells to detect optical signals requires additional signal detection, conversion, amplification, and processing systems. The data of circuit components is huge, and the number of circuit boards is large, which reduces the reliability of the system and poor equipment stability.

Images