Multi-resolution LBP textural feature extracting method

Abstract

The invention discloses a multi-resolution LBP (short for MR-LBR) textural feature extracting method, and belongs to the technical field of image information processing. The method includes the steps that firstly, an input image is preprocessed; secondly, image signals are decomposed and expressed through first-level discrete wavelet transformation, and a high-frequency mean chart is acquired; thirdly, rotation invariant unified LBP calculation is conducted on an original image, a low-frequency approximate subgraph and the high-frequency mean chart, and then an LBP histogram of the original image, an LBP histogram of the low-frequency similar subgraph and an LBP histogram of the high-frequency mean chart are acquired; eventually, the three histograms are spliced into a multi-resolution LBP histogram in a non-overlapping mode for describing texture information of the image. By the application of the method, more textural feature information of the image can be extracted, the defects of existing LBP in the texture processing aspect are overcome, and robustness of extracted features on rotation, illumination and the like is maintained. The multi-resolution LBP textural feature extracting method is applied to classification of fresh green tea leaves, the classification effect is remarkable, and accuracy reaches up to over 92 %.

Description

technical field [0001] The invention belongs to the technical field of image information processing, and in particular relates to a multi-resolution LBP texture feature extraction method (MR-LBP). Background technique [0002] Texture is an important visual cue, and it is one of the important features for people to describe and distinguish different objects. Texture analysis technology plays a very important role in the fields of image classification, image retrieval and industrial inspection. Generally speaking, image texture is easily affected by changes such as illumination and rotation. When the texture representation of the image cannot be extracted more accurately, texture classification becomes more difficult. Therefore, it is necessary to propose a new texture feature extraction method to solve these core problems. [0003] Now there are many texture feature extraction methods, such as: size-independent feature transformation (SIFT), gray level co-occurrence matrix...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a multi-resolution LBP texture feature extraction method (MR-LBP) to solve the loss of image part information during the binary quantization of the traditional LBP operator, and improve its ability to deal with irregular textures. , Insufficiencies in complex images with large sizes, and maintaining the robustness of extracted features to rotation and lighting, etc.

Images