Original Credence Recognition of handwritten digits based negative data

摘要：

Automatic recognition of original credence is the bottleneck of account information system. Atificial neural network is applied in the recognition. Negative data must be the necessary trained samples when trainning the classifier. The classifier could decrease some kind of recognition error. The error is that refuse recognition is not successful about input of negative data. The experiment results show that the classifier could deduce the error and the error rate reach the zero.

关键词： original credence negative data error recognition

作者: Deng Hongping

作者单位: College of Management, Huazhong University of Science and Technology, Wuhan, 430074, China

会议类型: 国际会议

会议名称: 第八届武汉电子商务国际会议(The Eighth Wuhan International Conference on E-Business)

会议地点: 武汉

会议语种:英文

页码: 1240-1245

在线出版日期: 2009-05-30（万方平台首次上网日期，不代表论文的发表时间）