A novel image retrieval method based on hybrid information descriptors

作者：Zhang, Ming; Zhang, Ke; Feng, Qinghe; Wang, Jianzhong; Kong, Jun^*; Lu, Yinghua

来源：Journal of Visual Communication and Image Representation, 2014, 25(7): 1574-1587.

DOI：10.1016/j.jvcir.2014.06.016

• Hybrid information descriptors (HIDs)
• Mutual information descriptors (MIDs)
• Self information descriptors (SIDs)
• Visual perception mechanism
• Image feature spaces
• Multi-scale analysis
• Content-based image retrieval (CBIR)
• Feature fusion

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.

• 出版日期2014-10
• 单位东北师范大学