A Fast and Compact Feature Based Approach to Face Recognition

摘要：

This paper presents a feature-based approach to face recognition where only a single example of each face is available for training. The approach relies on finding the facial measures and construction of facial feature vectors. The query facial vector is compared with the database by finding the least cost function. Techniques such as edge detection, tolerant subtraction are employed .The techniques are tested on a database of 50 images and a very encouraging result are achieved- The advantage of the approach is in its compactness and thus a high matching speed which makes it suitable for real time applications.

作者: Lovleen Bhatia Ashutosh Pandey Shishir Agrawal Dr. S.P.Singh

作者单位: Department of Electrical Engineering Institute of Technology,Banaras Hindu University, Varanasi - 22 Department of Electronics Engineering Institute of Technology,Banaras Hindu University, Varanasi - 2

会议类型: 国际会议

会议名称: 8th International Conference on Neural Information Processing(ICONIP 2001)(第八届国际神经信息处理大会)

会议地点: 上海

会议语种:英文

页码: 1664-1667

在线出版日期: 2001-11-14（万方平台首次上网日期，不代表论文的发表时间）