The Research of Image Segmentation based on Improved Neural Network algorithm

摘要：

Image segmentation is critical to image processing and pattern recognition, An image segmentation system is proposed for the segmentation of color image based on neural networks. First, we introduce BP Neural network, it has the capacity of parallel computing, distributed saving, self-studying, fault-tolearnt and nonlinear function approximating. So it widely used in image segmentation, but it also has some unavoidable defects. Based on this, a new method of image segmentation based on both Wavelet Decomposition and self-organizing map neural network (short for SOM-NN) is proposed. It has a greater ability on resisting noise, improving the convergence and so on. Color prototypes provide a good estimate for object colors. The image pixels are classified by the matching of color prototypes. The experimental results show that the system has the desired ability for the segmentation of color image in a variety of vision tasks.

关键词： Image segmentation Cluster Wavelet Decomposition self-organizing map

作者: Lijun Zhang Xunchun Deng

作者单位: Computer Science and Information Technology College Zhejiang Wanli University Qianhu South Road 8, NingBo, CHINA

会议类型: 国际会议

会议名称: Sixth International Conference on Semantics,Knowledge and Grids(第六届语义、知识与网格国际会议 SKG 2010)

会议地点: 宁波

会议语种:英文

页码: 395-397

在线出版日期: 2010-11-01（万方平台首次上网日期，不代表论文的发表时间）