Method for acquiring image shape feature descriptor

Abstract

The invention provides a method for acquiring an image shape feature descriptor, which comprises the following steps: S1, extracting a contour line of a color block connected domain of an input imageand position data of pixel points on the contour line, smoothing the contour line, and acquiring the smoothed contour line and a gravity center point of the color block connected domain; S2, performing coordinate conversion of the image standard pixel size on the boundary point of the linear interval in the smoothed color block connected domain contour line, the image gravity center point and theimage color block connected domain gravity center point; S3, obtaining a line length proportion number and a line direction interval angle proportion number of the converted line direction interval boundary center wheel line; and S4, performing numerical interval classification on the proportion number of the line length of the boundary center line, the proportion number of the angle number of theline direction interval, the proportion number of the line length of the image center line and the proportion number of the line angle of the image center line, and generating an image shape featuredescriptor. According to the method, the recall ratio and the precision ratio of image retrieval can be improved, and the matching effect of the same or similar images in image recognition retrieval is enhanced.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a method for acquiring image shape feature descriptors. Background technique [0002] Image descriptors are generally used to describe feature points. The image descriptors disclosed in the prior art are generally a set of vectors, including information such as position, direction, and scale of feature points. Common feature points are some stable points in the image, such as corner points, edge points, bright points in dark areas, dark points in bright areas, etc. A good set of descriptors should have distinction and commonality. Distinction means that the descriptor can reflect the feature points that distinguish one image from another, making the descriptor unique to the image; common Sexuality means that the descriptor can reflect an image and other identical or similar images with the same feature points, so that the descriptor has common feature points for the same or simi...

AI Technical Summary

Problems solved by technology

[0006] In view of the deficiencies of the above-mentioned prior art, the object of the present invention is to provide a method for acquiring image shape feature descriptors, aiming at solving the problem of non-uniform measurement units of image shape feature points or two Incomplete image comparability conditions lead to the problem that some identical or similar images cannot be retrieved, improve the recall and precision of image retrieval, and enhance the matching effect of identical or similar images in image recognition retrieval

Images