使用模糊竞争Hopfield网络进行图像分割

针对传统自组织竞争学习方法的不足,将模糊竞争学习引入竞争Hopfield网络中,由此设计了一个用于图像分割的模糊竞争Hopfield网络,通过将图像空间映射到灰度特征空间，实现灰度特征集的模糊聚类,进而实现图像分割.实验结果表明:对于二值分割,与Ostu方法相比，此算法在分割效果和对噪声的自适应能力方面具有明显的优点.对于多类分割,此算法比目前的FCM(fuzzy C mean)算法的处理速度要快.

Using Fuzzy Competitive Hopfield Neural Network for Image Segmentation

In this paper, based on the defect of self-organizing learning method, a fuzzy competitive learning method is proposed, and a fuzzy competitive Hopfield neural network for color image segmentation is designed based on competitive Hopfield neural network. The fuzzy clustering on gray feature set can be realized by means of mapping image space into gray feature space, then the color image segmentation can be done. The experiment results indicate that the algorithm is of better effect and adaptive ability to noise than Ostu method for binary segmentation, and shows higher processing speed than FCM (fuzzy C mean) algorithms for multi-class segmentation.