Topic
Eigenface
About: Eigenface is a research topic. Over the lifetime, 2128 publications have been published within this topic receiving 110119 citations.
Papers published on a yearly basis
Papers
More filters
21 Aug 2000
TL;DR: A novel method of face recognition based on individual eigen-subspaces is presented, which is expected to tackle such problems on face recognition as the ready availability of reference samples for each subject and the most intrapersonal difference and noise in the input.
Abstract: In this paper, a novel method of face recognition based on individual eigen-subspaces is presented, which is expected to tackle such problems on face recognition as the ready availability of reference samples for each subject. In the proposed method, multiple face eigensubspaces are created, with each one corresponding to one known subject privately, rather than all individuals sharing one universal subspace as in the traditional eigenface method. Compared with the traditional single subspace face representation, the proposed method captures the extrapersonal difference to the most possible extent, which is crucial to distinguish between individuals, and on the other hand, it throws away the most intrapersonal difference and noise in the input. Our experiments strongly support the proposed idea, in which 20% improvement of performance over the traditional "eigenface" has been observed when tested on the same face base.
14 citations
23 Aug 2004
TL;DR: In this paper feature extraction methods are outlined and the new method to compare to existing ones under impairments like changes in brightness, direction-of-illumination, hairstyle, clothing, expression, head orientation, and added noise is compared.
Abstract: We study the performance of a new eigenface-based method for face recognition. Specifically, we perform DCT preprocessing followed by the PCA-LDA combination. We compare the new method to existing ones (PCA, PCA-LDA, DCT-PCA) under impairments like changes in brightness, direction-of-illumination, hairstyle, clothing, expression, head orientation, and added noise. In this paper feature extraction methods are outlined. The results are obtained using two different face databases: the Aberdeen database from University of Stirling and the ORL database from University of Cambridge.
14 citations
TL;DR: The proposed biometric system uses an appearance based face recognition method called 2FNN (Two-Feature Neural Network), which uses neural networks to classify facial features and shows improvements over the existing methods.
14 citations
01 Oct 2006
TL;DR: The paper presents a system that consists of three stages that contribute in the face detection and recognition process that shows a high recognition rate when full frontal face images are led to the system.
Abstract: The paper describes an application of practical technologies to implement a low cost, consumer grade, single chip biometric system based on face recognition using infra-red imaging. The paper presents a system that consists of three stages that contribute in the face detection and recognition process. Each stage is explained with its individual contribution alongside results of tests performed for that stage. The system shows a high recognition rate when full frontal face images are fed to the system. The paper further discusses the application based approach in the automotive world with plans for further study. Recognition rates of the overall system are also presented.
14 citations
01 Dec 2003
TL;DR: In this paper, a more efficient way to implement eigenfaces (PCA) was introduced, which has now become a de facto and a common performance benchmark in face recognition.
Abstract: This paper introduces a more efficient way to implement eigenfaces (PCA) which has now become a de facto and a common performance benchmark in face recognition. The method of combining 2D DCT with PCA decreases the dimensionality of eigenvectors, and increases the perormance at the same time. Without any preprocessing step, the best recognition rate of our approach is 84.%, and outperforms the conventional eigenfaces method.
14 citations