269 / 2020-01-05 00:16:00

Cutset-type possibilistic c-means clustering image segmentation algorithm based on spatial neighborhood information

The cutset-type possibilistic c-means clustering (C-PCM) algorithm overcomes the coincident clustering problem of the possibilistic C-means clustering (PCM) algorithm by introducing the cut-set concept to modify the typicalities values. However, when the algorithm is applied to image segmentation, the algorithm does not consider the neighborhood information, which results in poor algorithm for noise image segmentation. This paper proposes a cutset-type possibilistic c-means clustering image segmentation algorithm based on spatial neighborhood information. The algorithm optimizes the typical values of pixels in the iterative process by utilizing the neighborhood information of each pixel in the image to correct some typicality values, thus improving the ability of typical values to characterize pixel correlation and improve performance of image segmentation. The simulation results show that the proposed algorithm can separate the target and background clearly for noisy images, especially for small target images.