Improved pixel relevance based on Mahalanobis distance for image segmentation

Image segmentation is to partition one given image into different regions. In essence, the procedure of image segmentation is to cluster the pixels into different groups according to the retrieved features. However, artefacts in the given images make the features be contaminated, resulting in poor performance of current segmentation algorithms. Therefore, how to reduce the effect of image artefacts is one hot topic in image processing. In current algorithms, neighbour information is adopted to resist the effect of image artefacts. However, when the image is contaminated with high-level noise, current algorithms also perform poor. Recently, non-local information is introduced to improve the quality of segmentation results, in which pixel relevance between pixels is crucial. In this paper, pixel relevance is measured based on Mahalanobis distance. More specifically, we consider the distribution of different samples and relevance interference between samples in the procedure of computing pixel relevance. Then, a new algorithm based on the novel pixel relevance is proposed, where non-local information can be incorporated into fuzzy clustering for image segmentation. The new algorithm can improve the robustness of corresponding algorithms greatly. Experiments on different noisy images show that the proposed algorithm can retrieve better results than conventional algorithms.