Image invariant feature extraction based on circular trace transform

Abstract

The invention relates to an image invariant feature extraction method based on the circular trace transform, and belongs to the field of image processing and computer vision. In this method, a circular trace line of the new circular trace transform is used to track an image, functional results on the circular trace line are mapped to a space generated by the three parameters of radius, length and angle, the result of the circular trace transform is obtained, the result is further subjected to functional integration, and image quadruple circular trace spatial features can be obtained. Different circular trace transform results can be obtained by using different functions on the circular trace line, that is, different texture properties of the image can be represented and multi-dimensional circular trace transform texture feature information is generated. According to the invention, the texture features extracted by the circular trace transform have an RST invariant property, deeper image information can be obtained, a better resolution capability is gained for images containing circular and arc-shaped textures, and the recognition capability is improved significantly in the case of fewer training samples.

Description

technical field [0001] The invention relates to an image invariant feature extraction method based on circular trace transformation, which belongs to the field of image processing and computer vision. Background technique [0002] Image feature extraction plays a key role in image processing. How to extract features that reflect the essence of the image and have strong adaptability from the image has always been the core research content in the fields of image processing and computer vision. As we all know, the most common image features include texture, color, and shape. In the process of extracting these features, researchers try to find some invariant features. When , these feature quantities are invariant. Image invariant feature analysis methods mainly include moment theory analysis method, correlation analysis, Fourier descriptor, autoregressive model, SIFT (Scale invariant feature transform, scale invariant feature transform), etc. The generalized analysis method, t...

AI Technical Summary

Problems solved by technology

[0004] Although many researchers have done a lot of research on the invariant feature extraction based on trace transformation, most of them are on the combination optimization of trace transformation functionals, analysis and research on the rotation invariance and scaling sensitivity of different functionals, and trace transformation. In terms of transformation application research, there are few studies on invariant feature extraction methods for images with different geometric textures, such as images with circular or arc-shaped textures.

Images