Face Recognition Based on Optimal Feed-Forward Neural Network

摘要：

This paper uses the KL transform to extract the features of the images,Second order item is omitted in Levenberg-Marquardt algorithm based on optimal theory,Avoid local minimum points and fast convergence,Combination for face recognition,Achieved a high recognition rate and good performance.The result of simulation testing shows that the method in this paper is feasible.

关键词： feature extraction Hesse matrix Face recognition

作者: HU Zhijun WANG Hongbin

作者单位: Department of Computer Science Xinzhou Teachers University Xinzhou,China

会议类型: 国际会议

会议名称: 2011 3rd International Conference on Computer and Network Technology(ICCNT 2011)(2011第三届IEEE计算机与网络技术国际会议)

会议地点: 太原

会议语种:英文

页码: 187-189

在线出版日期: 2011-02-26（万方平台首次上网日期，不代表论文的发表时间）