MULTI-RESOLUTIONAL GABOR FILTER IN TEXTURE ANALYSIS

The gabor filter approach is recently used in texture analysis. Among the existing applications, people convolve the given texture image wit h a set of gabor filters with some user-specified parameters. The conv olution takes a lot of time because of the large image size and the co mputational complexity. This paper utilizes the concept of multi-resol ution with parameter selection to do texture analysis. The computation time can be significantly reduced by diminishing the image size accor ding to several different sets of parameters. Experiments demonstrate that our strategy is quite efficient compared with the traditional gab or filter.