Handwritten Bangla Digit Recognition Using Hierarchical Bayesian Network

摘要：

A hierarchical Bayesian network is used for hand-written Bangla digit recognition.Rather than extractedfeature vectors,original digit images are used as thenetwork input directly.The network is trained onhandwritten samples.And then its tested on untrainedimages and hand-drawn digits.An average recognitionaccuracy of 87.5 is achieved The system exhibits ro-bust invariant recognition with respect to considerableobject noise which is quite common in handwrittendigits.

作者: Jin-wen Xu Jinhua Xu Yue Lu

作者单位: Department of Computer Science and Technology,East China Normal University,Shanghai Department of Computer Science and Technology,East China Normal University,Shanghai;Shanghai Researc

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 1096-1099

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）