节点文献

Generalized entropy mapping based neural network model and its application to image segmentation

推荐 CAJ下载
PDF下载
不支持迅雷等下载工具，请取消加速工具后下载。

【Author】 ZHENG Nanning ZHANG Yuanliang(Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an 710049, China)and LI Wenming(Department of Electrical Engineering, Keio University, Hiyoshi 3-14-1 Yokohama, Japan)

【机构】 Institute of Artificial Intelligence and Robotics； Xi’an Jiaotong University； Xi’an 710049； China)； Department of Electrical Engineering； Keio University； Hiyoshi 3-14-1 Yokohama； Japan)；

【摘要】 <正> A new neural network model for unsupervised pattern classification, which is known as generalized entropy mapping (GEM) , is presented. The framework, characteristics and performance of generalized information en-tropre neural network are discussed. The GEM can be used for image segmentation in computer vision system. The global optrmization net based on generalized entropy measure is given. The experimental results show that the performance of the GCM net is efficient in low-level visual information processing.更多还原

【Abstract】 A new neural network model for unsupervised pattern classification, which is known as generalized entropy mapping (GEM) , is presented. The framework, characteristics and performance of generalized information en-tropre neural network are discussed. The GEM can be used for image segmentation in computer vision system. The global optrmization net based on generalized entropy measure is given. The experimental results show that the performance of the GCM net is efficient in low-level visual information processing.更多还原

【关键词】 entropy； neural network； image segmentation； pattern recognition.；
【Key words】 entropy； neural network； image segmentation； pattern recognition.；

【基金】 Project supported by the National Natural Science Foundation of China (Grant No. 69735010).

【文献出处】 Progress in Natural Science ,自然科学进展(英文版) , 编辑部邮箱 ,1999年09期

【分类号】TP391.41
【下载频次】45

知网节下载

节点文献中：

本文链接的文献网络图示:

本文的引文网络

节点文献