A set of novel textural features based on 3D co-occurrence matrix for content-based image retrieval

This paper presents a set of novel texture features for content-based image retrieval (CBIR). CBIR require new algorithms for the automated extraction and indexing of salient image features, while texture features provide one important cue for the visual perception and discrimination of image content, so they are always one of the most popular representations in CBIR. The proposed features are based on the 3D co-occurrence matrix, and preliminary results show they are much better than traditional texture features. In this paper, experiments are made on an image database with 25000 images.