An adaptive fuzzy clustering algorithm based on multi-threshold for infrared image segmentation

Abstract

To obtain the satisfied performance of infrared image segmentation in complex environments, an adaptive fuzzy clustering algorithm based on multi-threshold (AFC_MT) is proposed. The methodology uses a coarse-fine concept to reduce the computational burden required for the fuzzy clustering and to improve the accuracy of segmentation that a single fuzzy clustering cannot reach. The coarse segmentation attempts to segment coarsely using the multithresholding technique. Firstly, the pseudo peaks in a multi-threshold algorithm are removed by introducing a control factor of peak areas and a control factor of peak widths to segment an image coarsely, then in order to find a finer segmentation result, the coarse segmentation result is clustered by an improved fuzzy clustering algorithm that introduces an adaptive function to get the most reason- able cluster number and that defines a logarithmic function as a measurement of distance. Experimental results show that AFC_MT behaves well in segmenting infrared images in complex environments.