Comparison of two gabor texture descriptor for texture classification
Xu Zhan, Xingbo Sun, Lei Yue-rong · 2009
Gabor texture descriptor have gained much attention fordifferent aspects of computer vision and pattern recogni-tion. Recently, on the rayleigh nature of Gabor filter out-puts Rayleigh model Gabor texture descriptor is proposed.In this paper, we investigate the performance of these two Gabor texture descriptor in texture classification. We built a texture classification system based on BPNN, and use thecorresponding feature vector from traditional Gabor texturedescriptor or Rayleigh model one as input of BPNN. We use three datasets from the Brodatz album database. For all the three datasets, the original texture images are subdi-vided into non-overlapping samples of size 32 × 32. 50%of the total samples are used for training and the rest areused for testing. We compare the system training time and recognition accuracy between two Gabor texture descriptor.The experimental results show that, it takes more time when using Rayleigh model Gabor texture descriptor than tradi-tional one, and the traditional Gabor texture descriptor ismore accuracy. Rayleigh model Gabor texture descriptor modifies texture descriptor with nearly half the dimension-ality and less computational expense, but it lose some per-formance compared with traditional one.