A Method of Image Contour Corner Detection Based on Centroid Distance Calculation

Abstract

The invention discloses an image contour corner point detection method based on centroid distance calculation. The corner point area is located by calculating the Euclidean distance between each image contour point and the centroid of the local area formed by it. The specific steps are as follows: first read the image, and extract the edge Contour, calculate the Euclidean distance between each pixel of the image contour and the centroid of the local area formed to form a distance set G, use upper and lower limit threshold processing and point threshold processing on G to form a set I, and finally for each element in I Each point applies the Harris corner detector to calculate the response, and the coordinates of the corresponding point with the strongest response in each element are the corner points. The present invention locates the corner area by calculating the Euclidean distance between each image contour point and the centroid of the local area formed, and the calculation result is less affected by the gray scale change of the image, which strengthens the immunity to noise and reduces the generation of false corner points. This method is suitable for computer vision fields such as image registration and matching, image fusion and object recognition.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image contour corner point detection method based on centroid distance calculation. Background technique [0002] Image corners are strong feature points of images, which are widely used in object recognition, image registration, motion detection and other fields. Existing corner detection methods include: corner detection based on grayscale images and corner detection based on binary images, wherein the Harris corner detection method based on grayscale images has the advantages of two-dimensional translation, rotation, and a small amount of illumination. Changes, a small amount of viewing angle changes are not sensitive, and the advantages of a small amount of calculation are widely used. [0003] The traditional Harris corner detection method is based on the gray value matrix of the block area formed by the pixel point as the center. When the illuminati...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the traditional Harris corner detection method, which is sensitive to noise when performing corner detection, the detection result is greatly affected by the change of image gray scale, and there are many false corners, and provides an image contour angle based on centroid distance calculation. Point detection method, this method can greatly reduce the impact of image gray level changes on corner positioning, avoid the weakening or loss of corner points, and reduce the generation of false corner points

Images