Texture image classification method based on BoF and multi-feature fusion

Abstract

The invention discloses a texture image classification method based on a BoF (bag of feature) and multi-feature fusion. The method comprises: performing local image selection on a texture image to form a fragment set; extracting GGCM (gray level-gradient co-occurrence matrix) features and SIFT (scale invariant feature transform) local features of all fragments, and performing importance weighted fusion on different features; generating a feature word for fusion feature clusters and performing preference and weighting on the words by using DWDPA (dynamic weighted discrimination power analysis), and assigning a fusion feature vector by using the preference and weighted word to form a training set fusion feature word bag model; computing the fusion feature vector of the texture image to be tested and acquiring a corresponding fusion feature word bag; and training the feature word bag model by using a SVM (support vector machine) as a classifier. The method effectively overcomes a defect that the GGCM is low in accuracy for large texture classification, compensates a weakness of information loss of the BoF feature space, and is more accurate and good in robustness.

Description

technical field [0001] The invention relates to a texture image classification method, in particular to a texture image classification method based on BoF and multi-feature fusion. Background technique [0002] Texture reflects the surface structure of an object, and is a macroscopic representation of a certain characteristic local repetitive pattern in an image, which can reflect some important features and properties of an object; texture analysis is an image processing process that extracts texture characteristic parameters to obtain a quantitative or qualitative description of texture. Texture classification is one of the important research directions of texture analysis research, and it has important applications in fields such as scene recognition, biometric recognition, remote sensing image analysis, medical image analysis, image retrieval, and moving object detection. [0003] Texture images can be expressed as the frequency of statistical texture primitives, which i...

AI Technical Summary

Problems solved by technology

The typical second-order statistical gray-level co-occurrence matrix can describe the relationship of the neighborhood gray-scale space in the texture pattern, which is an effective texture description method, but it is more suitable for the description of microtextures. For larger texture primitives Textures are poorly described

Images