New Statistics for Texture Classification Based on Gabor Filters

The paper introduces a new method of texture segmentation efficiency evaluation. One of the well known texture segmentation methods is based on Gabor filters because of their orientation and spatial frequency charac- ter. Several statistics are used to extract more information from results obtained by Gabor filtering. Big amount of input parameters causes a wide set of results which need to be evaluated. The evaluation method is based on the nor- mal distributions Gaussian curves intersection assessment and provides a new point of view to the segmentation method selection.

[1]  Kai H. Chang,et al.  Efficient edge detection and object segmentation using Gabor filters , 2004, ACM-SE 42.

[2]  Biao Hou,et al.  Unsupervised image segmentation based on the anisotropic texture information , 2004, International Conference on Image and Graphics.

[3]  Akira Ishikawa,et al.  About the Authors , 2001 .

[4]  Nicolai Petkov,et al.  Comparison of texture features based on Gabor filters , 2002, IEEE Trans. Image Process..

[5]  Nicolai Petkov,et al.  Comparison of texture features based on Gabor filters , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[6]  Cong Lin,et al.  Unsupervised image segmentation based on the anisotropic texture information , 2004, Third International Conference on Image and Graphics (ICIG'04).

[7]  Matti Pietikäinen,et al.  Outex - new framework for empirical evaluation of texture analysis algorithms , 2002, Object recognition supported by user interaction for service robots.

[8]  Marc Acheroy,et al.  Texture classification using Gabor filters , 2002, Pattern Recognit. Lett..