Robustness of Gabor Feature Parameter Selection

Gabor filters have been successfully used for feature extraction in many machine vision applications. In this study Gabor filtering based features are analyzed in terms of filter parameters to provide new insight into advantages of Gabor filters. Analytical and experimental results show that filter responses behave in a stable manner even while the parameter selection is suboptimal. In addition, restrictions are given for discrete domain filtering to expand continuous domain results for practical applications. There are no general methods for the selection of Gabor filter parameters, which is often a vague and application dependent task. Thus, behavior of filters in terms of parameters provides an important piece of knowledge. Considerations of performing the filtering in discrete domain are often neglected, while in this paper they are claimed to have an important impact,.