New image segmentation method using PCNN model based on optimal threshold

Pulse-coupled Neural Network (PCNN) has been widely used in image segmentation. However, satisfactory results are usually obtained at the expense of time-consuming selection of PCNN parameters and the number of iterations. This paper proposes a new method for image segmentation integrating optimal threshold with a simplified PCNN. The optimal threshold is based on the statistics of the original image which improves the exponentially decaying threshold of traditional PCNN and is much more suitable to human optic nature. The method initiates segmentation with the optimal threshold so only one time of iteration is needed. The method demonstrates accuracy and fast performance in segmentation results as well as in processing speed compared to those PCNN segmentation algorithms which requires determining the number of iterations and image entropy. Moreover, the method is not sensitive to noise and intensity. Experimental results show the effectiveness of the proposed method. This method aims to be possible in real-time hardware implementation.