Image Segmentation Method Based on Superpixel and Immune Sparse Spectral Clustering

Abstract

The invention discloses an image segmentation method based on superpixels and immune sparse spectrum clustering, which mainly solves the problems of low segmentation accuracy and poor robustness of the existing image segmentation methods. The steps of the method are as follows: first, divide the texture image into superpixels, extract its texture features, and use it as a feature data set; then, in the process of spectral clustering, combine the immune cloning algorithm and sparse representation to find the best similarity of the feature data set matrix; finally, the original image is marked according to the clustering label combined with superpixels to realize the segmentation of the texture image. The invention extracts the superpixel block of the image as a feature data set, and uses the image segmentation method based on immune sparse spectrum clustering to divide the feature data set, and obtains more accurate segmentation results.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image segmentation technology, which can be used for target recognition. Background technique [0002] Commonly used methods for image segmentation include threshold-based segmentation methods, edge-based segmentation methods, and region-based segmentation methods. With the development of pattern recognition and artificial intelligence theory, segmentation methods combined with specific theories have also been widely used. For example, based on Clustering segmentation technology, segmentation technology based on artificial neural network, segmentation technology based on genetic algorithm, etc. Among the existing clustering methods, spectral clustering is a clustering method with good characteristics of simple implementation, dimension-independent and global optimization. Applying spectral clustering to image segmentation is a hot research direction in th...

AI Technical Summary

Problems solved by technology

Although this method does not require prior knowledge and has low computational complexity, it still has the disadvantage of low segmentation accuracy.

Images