文章基本信息

标题：Object Based Geometrical and Texture Feature Extraction of Face from Front View
本地全文：下载
作者：Arun Kumar Nagdeve ; Somesh Kumar Dewangan
期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2012
卷号：3
期号：4
页码：726-730
语种：English
出版社：Ayushmaan Technologies
摘要：Face recognition has been a fast growing, challenging and interesting area in real-time applications. A large number of face recognition algorithms have been developed for decades. For recognition of face, feature extraction plays a crucial role. This paper presents the method for extracting the geometric and texture feature of face automatically from the front view, cumulative histogram approach is used for extracting geometric feature while co-occurrence matrices are used for extracting the texture feature of face. From the input image, face location is detected using the viola-Jones algorithm, from which different Object such as left eye, right eye, nose, and mouth area are cropped and is processed. For geometric feature extraction histogram of each Object is computed and its cumulative histogram values are employed by varying different threshold values to create the binary image of each Object, then simple linear search technique is applied to detect the corner end point of each object. For texture feature extraction, co-occurrence matrices of each object is determined, using this co-occurrence matrix, angular second moment, entropy, maximum probability of occurrence pixels, inverse difference, inverse difference moment , mean, contrast of each object is computed.
关键词：Object;Corner End Point;Linear Search;Cumulative Histogram; Gray Level Co-Occurrence Matrices (GLCM);Corelation (Corr); Angular Second Moment (ASM);Entropy;Maximum Probablity; Inverse Difference(ID);Inverse Difference Moment (IDM); contrast