Higher order statistics applied to image segmentation

Recent research has shown that image segmentation, has a great importance in many areas and especially in the industrial application, such as robot animation, mobile localization, etc...¶ Also, in medical imaging, it is used for tumor detection and in radar imaging, it is used for target detection. This paper deals with the problem of texture segmentation using higher order statistics. We propose a novel form of the third order statistics, extend the general concept of the cooccurrence matrix, and define a frequency matrix. First order, second order and third order statistics are analysed and applied on examples related to image segmentation. It is shown that third order statistics provide higher performance and better segmentation results than other methods. The experimental results are handled on twelve Bordatz textures images and then the obtained results are evaluated on using (i) first order statistics using gray level matrix, (ii) second order statistics using co-occurrence matrix and (iii) the third order statistics using frequency matrix. The experimental results demonstrate the importance of using the high order statistic in texture characterisation for image segmentation.