A non-integer step index PCNN model and its applications

Abstract

In this paper, based on the Simplified pulse coupled neural network (SPCNN) model, a non-integer step index PCNN model is proposed to solve “the mathematic coupled firing” phenomenon in classical PCNN. Method: A time parameter is introduced into SPCNN model, which make each iteration step value of SPCNN not an integer number any more, thus to emulate an analogue time system more closely. This model is used to accomplish two different tasks, detect microcalcifications in mammograms and detect noise in natural image. The experimental results show that the model performers better in microcalcifications detection. Furthermore, it is effectively to use this model in image noise reducing.