90年代发展形成的脉冲耦合神经网络（PCNN）模型特别适合于图像分割，边缘提取等方面的应用研究，但众所周知，PCNN模型图像分割效果不但取决于PCNN模型中各个参数的合理选择，而且同时还取决于循环迭代次数的确定选择准则，通常循环迭代次数N的选择通过人工交互方式来确。定正因如此选择合适的准则来确定N是PCNN图像分割的关键，但目前还没有文献提出一个合适的准则来解决这个问题。本文结合图像统计特性和PCNN参数模型提出了熵值最大准则。该准则实现了PCNN神经网络的自动图像分割。对于PCNN的理论研究和实际应用具有非常重要的现实意义。

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

Pulse Coupled Neural Network (PCNN) has gained widely research as a new artificial neural network. It derives directly from the studies of the small mammal's visual cortex. PCNN is a model with multiple parameters, and finding the proper values of these parameters is an onerous task. So a simplified PCNN is put forward and its performance in removing Gaussian noise of image is discussed in this article. The algorithm of PCNN combined with median filter and the step-by-step modifying algorithm, which is also based on PCNN, are proposed, and the experiment results of the two algorithms are analyzed and compared with that of median filter and wiener filter.

A new, simple method of counting and segmenting cell image is suggested in this paper. It is based on the feature of cell's logical and morphological iafornmation. By using of mathematics, n, morphological, logical operation and laplacian fiter, the method is realized with the MATLAH 5.10. The segment effect of this algorithm is tested with blood cell image in this article and the result is desirable, Particularly this method can count the number of blood cells. However, this counting is not very accurate, but it is enough for biological research of cytologlcal count. At the same time this method can segment special blood cell from its neighhorhood, which is very important for the development of image scgment technology, because traditional image segment method is inadequate to achieve such segment and count of calls.

The extremum and median filter can not only preserve the details of image as much as possible but aslo remove the noise when the grayscale changed gently. But, it's not very effective when processing those images including extremum areas. A new algorithm is presented in this paper and it solves the problem is presented in this paper and it solves the problem existing in formet filter. The experimental results show that the method is quite effective on most images and has better performance.