非监督图象分割的神经网络方法的研究

A NEURAL NETWORK APPROACH TO UNSUPERVISED IMAGE SEGMENTATION

本文提出了一种新的神经网络模型UMAN,以实现非监督的图象分割。该神经网络采用广义信息熵作为描述系统稳定和收敛的定量判据,克服了广义能量函数的缺陷;改进的Kohonen非线性映射结构,既突出了分类信息又减少了信息冗余;网络内部层和结点数由系统内部动态地确定,不需人工干预和先验知识;非监督自学习功能反映了低层次视觉信息处理的特点,可处理一般的图象,具有较强的适应性.实验结果表明该模型及算法是有效和实用的,具有一定的鲁棒性.

This paper proposes a new neural network model UMAN to perform unsupervised image segmentation. In the neural network, the generalized information entropy is used as the quantitative description and measurement of the system stability and asymptotication,and the disadvantage of generalized energy function is avoided. The improved Kohonen non-linear mapping structure not only contrasts the clustering features,but also reduces the redundant information. In the network,the internal layer and node numbers are determined dynamically by the system. The interaction and a prior knowledge are not required. The unsupervised self-learning function expresses the characteristics of the low-level visual information processing. The UMAN model can process various types of images and has strong adaptability. Experimental results show that the model and its algorithm are efficient, practical and robust.