Multilayer bitmap color feature-based image retrieval method

Abstract

The invention discloses a multilayer bitmap color feature-based image retrieval method. In the method, fast clustering is performed on an image with rich color information to obtain rational statistical distribution centers of each color cluster, and based on the rational statistical distribution centers, features capable of reflecting color differences among different distribution layers of the image are extracted to perform image retrieval. The method comprises the following steps of: first performing meshing on a color space of the queried image, counting the numbers of pixel points in each mesh and selecting the mesh with a number local maximum; then quickly generating each color cluster and the rational statistical distribution centers thereof by adopting a novel distance optimization algorithm and an equal-average nearest neighbor algorithm search (ENNS) algorithm in a K-average clustering algorithm, and on the other hand, performing space sub-block division on the queried image and calculating a Gaussian-weighted color average of sub-blocks; next comparing the color average of the image sub-blocks with the rational statistical distribution centers of the color clusters to extract the features of a K-layer bitmap; and finally performing the matched searching of the image features by combining the similarity measurements of the rational statistical distribution centers of the color clusters and the bitmap.

Description

Technical field: [0001] The invention relates to the fields of computer vision, image understanding and pattern recognition, in particular to an image retrieval method based on multi-layer bitmap color features. Background technique: [0002] With the rapid development of multimedia technology and the Internet, the retrieval of image information has become an urgent problem to be solved. Therefore, researchers have successively proposed various content-based image retrieval methods, using visual features such as color, texture, shape, and area. to characterize the content of the image. [0003] Among many visual features, color is the most basic and direct visual feature to describe image content, and is widely used in image retrieval technology. The traditional color feature-based image retrieval technology mainly extracts the color distribution statistical features such as the color histogram or the order moment of the image. Among them, the low-order moment of the image ...

AI Technical Summary

Problems solved by technology

Although this method has certain theoretical significance and rationality, since the extraction of local features of the bitmap depends on the global statistical features, and the global statistical features themselves are relatively rough, the local features extracted based on it are supplementary greatly reduced ability

In addition, these methods did not consider the relationship between color and human visual perception characteristics in the process of extracting features, and at the same time, they did not fully and effectively expand the range of information used when comparing image content differences, which affected the retrieval effect further improvement of

Images