Color Image Segmentation Using a Fuzzy Inference System

A novel method is proposed in the scope of image segmentation that solves this problem by breaking it into two main blocks. The first block's functionality is a method to anticipate the color basis of each segment in segmented images. One of the challenges of image segmentation is the inappropriate distribution of colors in the RGB color space. To determine the color of each segment, after mapping the input image onto the HSI color space, the image colors are classified into some clusters by exploiting the K-Means. Then, the list of cluster centers is winnowed down to a short list of colors based on a set of criteria. The second block of the proposed method defines how each pixel of the input image is mapped onto a specified list of segmentation centers (obtained from the previous block). Usage of the Fuzzy Inference System (FIS) is the solution of this paper to allocate a segmentation center to each image pixel. The rules which the FIS utilizes are designed based on the color of each pixel and its nearby neighborhood. To assess the capability of this method, it is applied to the BSDS500 dataset. The structure of proposed method causes the ability of parallel programming which speeds up the run-time. The experimental results illustrate the superiority of the proposed method over the state-of-the-art methods in the image segmentation.