文章基本信息

标题：Face Recognition using Weighted Distance Transform
本地全文：下载
作者：Muhammad Ashraf ; Muhammad Sarim ; AbdulBasit Shaikh 等
期刊名称：Research Journal of Recent Sciences
电子版ISSN：2277-2502
出版年度：2014
卷号：3
期号：9
页码：19-25
语种：English
出版社：International Science Community Association
摘要：In recent years the task of ecognizing human face with the help of a machine has acquired a significant attention among researchers. A wide range of commercial and law enforcement applications largely accounts for this developing trend. Although current face ecognition systems have reached a certain maturity level they are still far away from the capability of human perceptual system. In a 2D image the unique facial appearance normally consists of intensity curvatures which may be incorporated for ecognizing human face. This work inestigates the use of weighted distance transform to bring improvements in face ecognition. The weighted distance transform takes into account both the spatial distance among pixels and the local intensity variations. A standard face dataset is used to alidate the proposed method. The obtained results are comparable to the state-of-the-art face recognition techniques.
关键词：Weighted distance;geodesic paths;face;recognition;fast marching;facial curvature