Segmentation of textures using PCA fusion based Gray-Level Co-Occurrence Matrix features

In this paper, segmentation of textures using principle component analysis (PCA) fusion based Gray-Level Co-Occurrence Matrix (GLCM) features in image segmentation is presented. First, four of the most common Haralick´s features are calculated. Second, we perform principal component analysis to convert the 4 features extracted data in to four principal components. Then, choose fused coefficient according to PCA-based weighted average rule. Finally, k-means cluster algorithm has been applied for fusion image, the segmentation results has been obtained. The experiments demonstrate that the proposed approach is effective and is able to achieve favorable results in terms of precision.