Performance Study of Gabor Filters and Rotation Invariant Gabor Filters

C. B. Richard Ng, Guojun Lu, Dengsheng Zhang
Gippsland School of Computing and Info Tech.
Monash University, Australia

 

          Gabor filters have been proven to be very useful for texture retrieval and are widely adopted. However, the original Gabor texture features are rotation variant. Recently, Zhang et al proposed rotation normalization using circular shift. They have shown the proposed rotation normalization is effective through some examples, but did not comprehensively study its performance. The purpose of this paper is to study the performance of the rotation normalization on a good size texture database. Our experimental results show that the proposed rotation normalization is effective in retrieving rotated textures and has some adverse effect on retrieving non-rotated texture.

Index Terms- Gabor filter, CBIR, texture and rotation invariance