Inner hole wall image distortion correction method and system and medium

Abstract

The invention provides an inner hole wall image distortion correction method and system and a medium. The inner hole wall image distortion correction method comprises the steps of an image and parameter obtaining step: obtaining an original distortion image and geometric parameters in an inner hole shooting process; a conversion relation obtaining step: calibrating a camera, and obtaining a conversion relation between image pixels and a real size; and a distortion image correction step: obtaining a distortion image after lens distortion correction according to the obtained original distortionimage, the geometric parameters of the inner hole shooting process and the conversion relation between the image pixels and the real size. According to the invention, correction of inner hole wall surface image distortion shot by an industrial endoscope can be automatically completed, and further development of a defect detection system based on machine vision is facilitated.

Description

technical field [0001] The invention relates to the technical field of machine vision defect detection, in particular to a method, system and medium for correcting image distortion on the wall surface of an inner hole. Background technique [0002] Machine vision defect detection technology based on industrial endoscope is an automatic detection technology. In the actual inspection process, after the endoscope is inserted into the inner hole to be inspected through a mechanical device, the system can automatically take a series of images of the inner hole and obtain the number and size of defects on the surface of the inner hole through image processing and recognition algorithms. This automatic detection technology can replace the traditional naked eye detection method, which is helpful to improve the detection accuracy of product quality and reduce the labor intensity of workers, so it has been extensively researched and practiced. However, the current inner hole defect d...

AI Technical Summary

Problems solved by technology

However, the current inner hole defect detection technology mostly adopts the shooting angle along the inner hole axis, which leads to a high degree of deformation of the shape of the inner hole wall and a large loss of information, resulting in large errors in the shape and size of the defect after image distortion correction

One solution is to adopt a lateral shooting angle perpendicular to the axis of the inner hole. Although the shooting efficiency is low, the information loss is small and the detection accuracy is higher

The image obtained from the side view also has a certain shape distortion because the object is a cylinder, which will affect the final defect identification and detection results.

Images