An Improved Pixon-Based Approach for Image Segmentation

An improved pixon-based method is proposed in this paper for image segmentation. In thisapproach, a wavelet thresholding technique is initially applied on the image to reduce noise and toslightly smooth the image. This technique causes an image not to be oversegmented when the pixonbasedmethod is used. Indeed, the wavelet thresholding, as a pre-processing step, eliminates theunnecessary details of the image and results in a fewer pixon number, faster performance and morerobustness against unwanted environmental noises. The image is then considered as a pixonal modelwith a new structure. The obtained image is segmented using the hierarchical clustering method (FuzzyC-Means algorithm). The experimental results in this paper indicate that the proposed pixon-basedapproach has a reduced computational load and a better accuracy compared to the other existing imagesegmentation techniques.