Scene Image Classfying mage via the Partially Connected Neural Network

摘要：

This paper presented a new method for scene images classification via Partially Connected Neural Network. The neural network has a mesh structure in which each neuron maintain a fixed number of connections with other neurons. In training, the evolutionary computation method was used to optimize the connection target neurons and its connection weights. The model is able to receive a large number of inp input neurons and make it possible that classification of scene images needed neither any image preprocessing nor any feature extraction. Thus, the new method overcome the bug that loss and uncertainty of image information brought by man man-made feature selection in the past. A large-scale GPU parallel computing method was used to accelerate neural network training. Though experiments of the method, we report a satisfactory classification performance especially for the scene images which contain artificial objects.

关键词： Scene images classification:Partially connected neural network:GPU parallel computing

作者: Li-lan Pan Yue Zhang

作者单位: College of Mechanical and Electrical Eng.Nanjing University of Aeronautics and Astronautics,Nanjing, Department of Cognitive Science Xiamen University Xiamen,China

会议类型: 国际会议

会议名称: The 5th International Conference on Computer Science & Education(第五届国际计算机新技术与教育学术研讨会 ICCSE10)

会议地点: 合肥

会议语种:英文

页码: 1789-1793

在线出版日期: 2010-08-24（万方平台首次上网日期，不代表论文的发表时间）