A novel image retrieval method based on hybrid information descriptors

•A set of descriptors based on human visual perception mechanism are proposed.•The descriptors utilize image structure to explore the feature internal correlations.•Visual features extract with multi-scale analysis.•A visual optimization model is presented for feature fusion.•Highly effective and precise retrieval performance is shown.

In this paper, we propose a novel image retrieval method called hybrid information descriptors (HIDs) consisting of mutual information descriptors (MIDs) and self information descriptors (SIDs). Based on the physiological structure of human eyes and visual perception mechanism, HIDs are designed to explore the internal correlations among different image feature spaces with image structure and multi-scale analysis, not only characterizing the low-level features, such as color, shape and texture, but also imitating the process of visual information transfer and perception in high-level understanding with the help of the proposed visual optimization model for feature fusion. Comparing with other existing methods applied to content-based image retrieval (CBIR) on four datasets, the usefulness and effectiveness of the HIDs are shown. Extensive experimental results can also demonstrate this.