Handwritten Character Recognition Research Based on Adaptive Minimum Distance Classifiers Integration

摘要：

　　It is difficulty to gain completely satisfactory effect if a single classification is used to check a complicated recognition classification problem.Using the complementarities between the different classify method,integrating many classifiers,it can reduce the identification mistake and strengthen recognition robustness.Taking a offiine handwritten number recognition system as an example,adopting Bayesian discriminate function based on minimal mistake rate,uniting recognition algorithm of RBF kernel function,using Bagging technology,adaptive minimum distance classifiers integration is designed in which there is minimal mistake rate.Furthermore,an offiine handwritten number recognition system in high accuracy is exploited in which there is adaptive and self-learning function.It can be used for important economic fields such as financial statement and bank paper.

关键词： Character recognition RBF kernel function Minimal mistake rate Classifiers integration Recognition system

作者: TANG Zhaoping SUN Jianping ZHONG Lusheng

作者单位: Key Laboratory of Ministry of Education for Conveyance and Equipment, East China Jiao Tong University, Nanchang Jiangxi, 330013, China

会议类型: 国际会议

会议名称: the 2010 International Conference on Frontiers of Manufacturing and Design Science(第一届制造与设计科学国际会议(ICFMD 2010))

会议地点: 重庆

会议语种:英文

页码: 3388-3392

在线出版日期: 2010-12-11（万方平台首次上网日期，不代表论文的发表时间）