Rotation Invariant Texture Classification Using Circular Gabor Filter Banks

This paper presents a new method for rotation invariant texture classification based on the circular Gabor wavelets. A circular Gabor filter bank is proposed to decompose an image into multiple scales and be rotation invariant. By the mean and variance of the circular Gabor filtered image, a discriminant can be found to classify rotated images. In the primary experiments, comparatively high correct classification rates were obtained using a large test sample set.