Eigenface

About: Eigenface is a research topic. Over the lifetime, 2128 publications have been published within this topic receiving 110119 citations.

Using discrete wavelet transform and eigenfaces for recognizing avatars faces

Abstract: It has been observed that the security of virtual worlds is becoming an important issue for law enforcement agencies. Accurate and automatic tracking of people in the virtual world is an interesting problem for terrorism and security experts. One way to track and recognize the identity of a person in the virtual world is to recognize the face of the avatar that represents this person. To deal with this problem two algorithms capable of recognizing avatar faces with a high degree of accuracy are described in this paper. Experiments conducted on two datasets of avatars from the Second Life and Entropia Universe virtual worlds show the effectiveness of using these algorithms for recognizing avatar faces.

Face recognition using Active Appearance Model

Abstract: In this paper a framework for face recognition using Active Appearance Model is proposed. Active appearance model has the ability to synthesize near-photo realistic images of the class learned from the training set. The recognition algorithm works on those synthesized images and tries to match the nearest face in the training set to the synthesized image.

An improved face recognition method using Local Binary Pattern method

Abstract: Security system based on biometrics is becoming more popular everyday as a part of safety and security measurement against all kind of crimes. Among several kinds of biometric security systems, face recognition is one of the most popular one. It is one of the most accurate, mostly used recognition methods in modern world. In this paper, two most popular face recognition methods have been discussed and compared using average image on Yale database. To reduce calculation complexity, all training and test images are converted into gray scale images. The whole face recognition process can be divided into two parts face detection and face identification. For face detection part, Viola Jones face detection method has been used out of several face detection methods. After face detection, face is cropped from the actual image to remove the background and the resolution is set as 150×150 pixels. Eigenfaces and fisherfaces methods have been used for face identification part. Average images of subjects have been used as training set to improve the accuracy of identification. Both methods are investigated using MATLAB to find the better performance under average image condition. Accuracy and time consumption has been calculated using MATLAB code on Yale image database. In future, this paper will be helpful for further research on comparison of different face recognition methods using average images on different database.

Robust Discriminant Analysis of Gabor Feature for Face Recognition

Abstract: This paper introduces a robust discriminant analysis of Gabor feature (RGF) method for face recognition. The RGF method apply a novel robust Fisher linear discriminant model (RFM) to the low dimensional Gabor feature defined by principle component analysis. The robustness of the RGF method comes form the new RFM which improves the generalization capability of the FLD by robust estimate of the within-class scatter matrix. The feasibility of the RGF method has been successfully tested on face recognition using 1400 images from ORL and FERET database. The effectiveness of the RGF method is shown in term of both the excellent accuracy (99% and 97.75%) and the comparative performance against some popular face recognition schemes such as the eigenfaces, the Fisherfaces, and the Gabor-Fisher classifier method.

Face Recognition Machine Vision System Using Eigenfaces

Abstract: Face Recognition is a common problem in Machine Learning. This technology has already been widely used in our lives. For example, Facebook can automatically tag people's faces in images, and also some mobile devices use face recognition to protect private security. Face images comes with different background, variant illumination, different facial expression and occlusion. There are a large number of approaches for the face recognition. Different approaches for face recognition have been experimented with specific databases which consist of single type, format and composition of image. Doing so, these approaches don't suit with different face databases. One of the basic face recognition techniques is eigenface which is quite simple, efficient, and yields generally good results in controlled circumstances. So, this paper presents an experimental performance comparison of face recognition using Principal Component Analysis (PCA) and Normalized Principal Component Analysis (NPCA). The experiments are carried out on the ORL (ATT) and Indian face database (IFD) which contain variability in expression, pose, and facial details. The results obtained for the two methods have been compared by varying the number of training images. MATLAB is used for implementing algorithms also.