A correction method of cheese side image under machine vision

Abstract

The invention relates to a method for correcting cheese side images under machine vision. Based on perspective projection, an imaging model of cheese side images is established to obtain cheese side images; point coordinates in a world coordinate system corresponding to an image coordinate system are converted As the homogeneous coordinates, the internal parameter matrix and external parameter matrix of the camera are obtained, and the external parameter matrix is ​​combined with the internal parameter matrix to obtain the transformation matrix; the relationship between the points on the cheese surface and the image projection points is expressed by a homogeneous equation, according to The point coordinates in the corrected cheese side image are calculated by the sub-equation, and the gray value of each point is reset to obtain the corrected cheese side image. The cheese side image correction method under machine vision proposed by the invention can better correct distorted cheese images of various diameters, and has a good restoration effect on the straight line characteristics of the upper and lower boundaries of the cheese side image.

Description

Technical field: [0001] The invention belongs to the field of digital image processing, and in particular relates to a cheese side image correction method under machine vision. Background technique: [0002] Package yarn is the output product of the winding process in spinning mills, its quality directly affects the production of subsequent processes, and ultimately affects the quality of textiles. Restricted by factors such as the setting of the production process, inadequate cleaning and maintenance of equipment, and the quality of raw materials, the cheese may have defects, and the cheese needs to be inspected. One of the inspection methods is based on machine vision. [0003] When machine vision is used to detect the external shape of cheese, the captured image needs to be consistent with the shape of the actual cheese. Usually, the camera model is an idealized small hole imaging model. In actual imaging, the image collected by the camera There is always a certain nonli...

AI Technical Summary

Problems solved by technology

With the advancement of modern technology, the distortion caused by the hardware of the imaging system is getting smaller and smaller, but it cannot be eliminated fundamentally. In terms of machine vision, accurate images can improve the accuracy of the detection system. Generally, the side image of the package yarn collected In , the distortion of the linear characteristics of the upper and lower boundaries of the cheese profile is serious, so it is necessary to correct the cheese image in the vertical direction

Images