Improving Shape-Based CBIR for Natural Image Content Using a Modified GFD

We present a modified version of the Generic Fourier Descriptor (GFD) that operates on edge information within natural images from the COREL image database for the purpose of shape-based image retrieval. By incorporating an edge-texture characterization (ETC) measure, we reduce the complexity inherent in oversensitive edge maps typical of most gradient-based detectors that otherwise tend to contaminate the shape feature description. We find that the proposed techniques not only improve overall retrieval in terms of shape, but more importantly, provide for a more accurate similarity ranking of retrieved results, demonstrating greater consideration for dominant internal and external shape details.

[1]  Guojun Lu,et al.  A Comparative Study of Three Region Shape Descriptors , 2001 .

[2]  Ling Guan,et al.  Minimizing human-machine interactions in automatic image retrieval , 2004, Canadian Conference on Electrical and Computer Engineering 2004 (IEEE Cat. No.04CH37513).

[3]  Hanan Samet,et al.  Content-based image retrieval using Fourier descriptors on a logo database , 2002, Object recognition supported by user interaction for service robots.

[4]  Guojun Lu,et al.  Generic Fourier descriptor for shape-based image retrieval , 2002, Proceedings. IEEE International Conference on Multimedia and Expo.

[5]  Dengsheng Zhang.  Image retrieval based on shape , 2002 .

[6]  Ling Guan,et al.  A neural learning approach for adaptive image restoration using a fuzzy model-based network architecture , 2001, IEEE Trans. Neural Networks.