Characteristic matching method based on bilateral matching and trilateral restraining

Abstract

The invention belongs to the technical field of image processing, relating to a characteristic matching method based on bilateral matching and trilateral restraining. The method comprises the following steps of: obtaining initial points with a bilateral matching arithmetic; reorganizing the initial points with trilateral triangulation arithmetic; and using the characteristic matching arithmetic based on the trilateral restraining to achieve a result for improving the correction rate of matching points and increasing the number of the correct matching points. For most geometrical transformation and light transformation, the method comprises rotation transformation, scale transformation, fuzzy transformation, visual angle change, JPEG compression and light intensity change, is more robust, and can obviously improve the correction rate of the matching points and the number of the matching points, thereby having wider application field, being capable of obtaining a better characteristic matching result, and having higher practical applicability.

Description

technical field [0001] The invention belongs to the technical field of image processing and relates to a feature matching method. Background technique [0002] There are many major issues in the field of computer image processing technology, such as symmetry detection [5], wide baseline matching [9] and panorama construction [2]. exact match. Now there are many feature extraction methods, such as Harris corner detection algorithm [3], SIFT [7] and SURF [1], these algorithms can extract stable features with discrimination. However, the measure of feature similarity is limited by existing methods. The most important method now is to do vector dot product on the descriptor, and then compare whether the ratio between the first neighbor and the second neighbor is greater than a certain predefined threshold, so as to select an approximate match with a greater similarity. This method We call it the Original Matching Method (OMM). Although this strategy can effectively remove th...

AI Technical Summary

Problems solved by technology

Although this strategy can effectively remove the influence of changes in geometry and light, it may also remove features that should be correctly matched.

Recently, some new similarity matching methods have been proposed, such as spectral technology based on the pairing principle [6], CEMD [8], these methods improve the matching accuracy, but ignore a large number of points that should be matched

Images