The iterative convolution–thresholding method (ICTM) for image segmentation

Variational methods, which have been tremendously successful in image segmentation, work by minimizing a given objective functional. The functional usually consists of fidelity term and regularization term. Because functionals may vary from different types images, developing an efficient, simple, general numerical method to minimize them has become increasingly vital. However, many existing methods are model-based, converge relatively slowly, or involve complicated techniques. In this paper, we develop novel iterative convolution–thresholding (ICTM) that is applicable wide range variational models for segmentation. ICTM, the interface between two segment domains implicitly represented characteristic functions domains. written into linear functions, approximated terms heat kernel convolution. This allows us design approximate energy. energy-decaying property, thus unconditional stability theoretically guaranteed. Numerical experiments show easy implement, robust, various segmentation models.