Automated image segmentation using improved PCNN model based on cross-entropy

Abstract

The pulse coupled neural network (PCNN) is a new neural network that was developed and formed in the 1990's. The key point of a PCNN is the modulated coupling mechanism, while coupled results produce internal activity. The output of the PCNN is a binary image sequence, which can be considered the result of threshold segmentation. In this paper, the matrix made by the internal activity is regarded as a breadth of image, which then can be conjoined with the technique of traditional threshold segmentation. The application of the minimum cross-entropy criterion in the technique of image segmentation makes the discrepancy of information content between segmented image and image after segmentation to be minimal. A kind of novel of image segmentation algorithm based on automatic cycle iterations is put forward, after the traditional PCNN threshold segmentation mechanism is improved in combination with the minimum cross-entropy criterion. Theory analysis and experimental results all show that the best segmentation output can be drawn using this new algorithm.