GLASS PATTERN RECOGNITION BASED ON IMPROVED BP ALGORITHM

摘要：

　　According to the characteristics of glass defects,through analyzing the advantages and disadvantages of the traditional BP algorithm,an improved BP neural network recognition algorithm based on neural network classifier is proposed.The improved algorithm is applied to the glass defect classification and character recognitionin.Compared with traditional BP recognition algorithm,experimental results show that,identification of false positives is low by improving the algorithm of fast convergence.

关键词： Glass defect BP neural network Feature extraction Pattern recognition

作者: Shufang Li Lihui Zhang

作者单位: Department of Information Engineering,Environmental Management College of China,Qinhuangdao 066004,China

会议类型: 国际会议

会议名称: 2012 2nd IEEE International Conference on Cloud Computing and Intelligence Systems (2012年第2届IEEE云计算与智能系统国际会议(IEEE CCIS2012))

会议地点: 杭州

会议语种:英文

页码: 98-103

在线出版日期: 2012-10-30（万方平台首次上网日期，不代表论文的发表时间）