Local texture description method based on local grouping comparison mode column diagram

Abstract

The invention provides a local texture description method based on a local grouping comparison mode column diagram. The method specifically comprises the following steps: step 1, selecting q supporting regions on the basis of an interest region; step 2, normalizing the supporting regions into circular regions; step 3, dividing circular images into P parts through convergence strategies based on mean value ordering; step 4, calculating a local grouping comparison mode of pixel coordinate points inside the circular images; step 5, counting a local grouping comparison mode column diagram in a local characteristic region according to the suffix of the local grouping comparison mode, so as to form local texture description of a single supporting region; step 6, cascading the local texture descriptions of the supporting regions to obtain a local grouping comparison mode column diagram for characteristic regions, and forming a local texture descriptor. According to the method, actually, a gray change column diagram for pixel point neighbourhood pixels with consistent gray values is calculated, and the descriptor formed by the method is strong in discrimination performance and has excellent robustness in illumination transformation and geometric transformation.

Description

technical field [0001] The invention relates to a method for describing texture features of local images in the field of computer vision, in particular to a method for describing local textures based on histograms of local grouping contrast patterns. Background technique [0002] Due to the characteristics of good discrimination, high reproducibility, strong robustness, and robustness to geometric changes and illumination changes, the local features of images are widely used in image and video retrieval, image registration, target tracking, target recognition, target classification, Texture classification, robot localization, wide-baseline matching, etc. have been widely used. [0003] The research on image local features includes three aspects: feature extraction, feature description and feature matching. The research on image local feature extraction has been relatively mature. The most attention now is the local image feature description, which is held every year at the...

AI Technical Summary

Problems solved by technology

Although this method has achieved good discrimination and robustness, there are still the following problems: the full arrangement of pixel neighbors has a great relationship with the number of selected neighbors, which is the factorial of the number of neighbors

Although quantization solves the histogram sparse problem that may be caused by a large number of full permutations, the amount of calculation is too large, and quantization further increases the amount of calculation

Images