A Method of Irregular Workpiece Detection Based on Machine Vision

Abstract

The invention relates to a method for detecting irregular workpieces based on machine vision. By acquiring images of irregular workpieces and performing edge detection, the edges of the workpiece images are converted into polar coordinates, and the polar coordinates are set in different positions by Hough transform. θ The intersection of the connecting lines in the horizontal direction is used as a new two-dimensional plane, and the missing points are obtained by judging the intersection points according to the information gain of all connecting points in the two-dimensional plane. If there are no bubbles in the inspected area, there is no defect in the workpiece. If there are bubbles in the missed inspection area, the edge area of ​​the bubbles in the missed inspection area is obtained, and the volume and sum of all bubbles in adjacent frames and single-frame images are analyzed according to the edge area of ​​the bubbles. Position change, determine the exact position of the missed detection defect, based on machine vision, comprehensive analysis, more accurate positioning of the defect position of the irregular detection workpiece, high detection accuracy and strong practicability.

Description

technical field [0001] The present application relates to the field of air tightness detection, in particular to a method for detecting irregular workpieces based on machine vision. Background technique [0002] At present, many methods have appeared in the technology used in air tightness testing experiments, such as: bubble detection method, air pressure detection method, chemical gas loss method, etc. The bubble detection method is currently the most economical and practical method. Inflate or inflate during the testing process to obtain the air bubbles for air tightness testing, and observe the air bubbles in the water by soaking the workpiece into water to judge the airtightness of the workpiece. However, during the air tightness testing, if irregularities For workpieces, simple detection of air bubbles in water may easily lead to missed and wrong detections. Due to the irregularity of the workpiece, some defect bubbles at the corners of the back cannot surface after o...

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a method for detecting irregular workpieces based on machine vision to solve the problems of missed detection and false detection that may exist in the existing irregular shape analysis of detection workpieces. The following technical solutions are adopted:

Images