Image Moment Based Registration Scheme Utilizing Support Vector Machine

摘要：

A novel image registration scheme is proposed in this paper. Six low order image moments are used as image global pattern features and are feed into support vector machine to estimate translation, rotation and scaling parameters. Simulation results show that the proposed registration scheme is accurate and robust to noise.

关键词： image registration support vector machine image moment

作者: Wu Jianzhen

作者单位: Department of Automation Shanghai University of Engineering Science Shanghai,China

会议类型: 国际会议

会议名称: The Fifth International Conference on Information Assurance and Security(第五届信息保障与安全国际会议)

会议地点: 西安

会议语种:英文

页码: 575-577

在线出版日期: 2009-08-18（万方平台首次上网日期，不代表论文的发表时间）