In this paper, we focus on invariant texture segmentation, and propose a new method using circular Gabor filters (CGF) for rotation invariant texture segmentation. The traditional Gabor function is modified into a circular symmetric version. The rotation invariant texture features are achieved via the channel output of the CGF. A new scheme of the selection of Gabor parameters is also proposed for texture segmentation. Experiments show the efficacy of this method.
Citation:
Jainguo Zhang, Tieniu Tan, Li Ma, "Invariant Texture Segmentation Via Circular Gabor Filters," icpr, vol. 2, pp.20901, 16th International Conference on Pattern Recognition (ICPR'02) - Volume 2, 2002