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
01 Sep 2019
TL;DR: This research aims to examine the performance of the PCA-Eigenface method to recognize human face images from several databases that have their own challenges, such as the lack of illumination of facial images, significant variations in expression and the use of accessories such as glasses.
Abstract: Eigenface is an algorithm in the principal component analysis (PCA) that is used to recognize faces. Eigenface used to reduce dimensionality and find the best vector for distributing the facial image in the facial space. This method has been widely used and implemented in various previous researches to recognize human face images. Not only to detect human faces under normal conditions, but PCA has also been proven to be able to properly recognize images in various expressions. It can even recognize facial images with various challenges such as detecting faces after plastic surgery and combining them with facial image reconstruction techniques. This research aims to examine the performance of the PCA-Eigenface method to recognize human face images from several databases that have their own challenges, such as the lack of illumination of facial images, significant variations in expression and the use of accessories such as glasses. The recognizable accuracy is quite varied, from 100% to 67% in each database with and with an average recognition of more than 85%.
7 citations
25 Aug 2004
TL;DR: A new method of isolating useful qualities from a range of image subspaces using Fisher's linear discriminant and combining them to create a more effective image subspace, utilising the advantages offered by numerous image processing techniques and ultimately reducing recognition error.
Abstract: The application of image processing as a pre-proces sing step to methods of face recognition can signif icantly improve recognition accuracy. However, different image pro cessing techniques provide different advantages, en hancing specific features or normalising certain capture conditions. We introduce a new method of isolating these usef ul qualities from a range of image subspaces using Fisher's linear disc riminant and combining them to create a more effect ive image subspace, utilising the advantages offered by numer ous image processing techniques and ultimately reducing recognition error. Systems are evaluated by performing up to 2 58,840 verification operations on a large test set of images presenting typical difficulties when performing recognition. Results are presented in the form of error rate cur ves, showing false acceptance rate (FAR) vs. false rejection rate (FRR ), generated by varying a decision threshold applie d to the euclidean distance metric performed in combined face space.
7 citations
27 Jul 2016
TL;DR: Through the analysis and comparison of the experimental results, it is proved that this algorithm can achieve the efficient recognition of face images, and has better robust performance when dealing with large sample database.
Abstract: The principal component analysis (PCA) is one of the most commonly used feature extraction methods in face recognition, but the traditional PCA method can't deal with the non-linear problem between pixels. In this paper, based on the traditional PCA, combined with the advantages of KPCA(kernel-PCA), a new composite kernel-PCA algorithm is designed. By combining the two single kernel functions, the new algorithm can make full use of their complementary characteristics. Experiments were performed on ORL and FERET face database respectively. Through the analysis and comparison of the experimental results, it is proved that this algorithm can achieve the efficient recognition of face images, and has better robust performance when dealing with large sample database.
7 citations
TL;DR: This paper proposed a theoretically efficient approach for face recognition based on principal component analysis (PCA) and rotation invariant uniform local binary pattern texture features in order to weaken the effects of varying illumination conditions and facial expressions.
Abstract: This paper proposed a theoretically efficient approach for face recognition based on principal component analysis (PCA) and rotation invariant uniform local binary pattern texture features in order to weaken the effects of varying illumination conditions and facial expressions. Firstly, the rotation invariant uniform LBP operator was adopted to extract the local texture feature of the face images. Then PCA method was used to reduce the dimensionality of the extracted feature and get the eigenfaces. Finally, the nearest distance classification was used to distinguish each face. The method has been accessed on Yale and ATR-Jaffe face databases. Results demonstrate that the proposed method is superior to standard PCA and its recognition rate is higher than the traditional PCA. And the proposed algorithm has strong robustness against the illumination changes, pose, rotation and expressions.
7 citations
05 Nov 2007
TL;DR: In this article, an alternative formulation of orthogonal locality preserving projections (OLPP) is proposed, which introduces Schur decomposition in locality preserving projection (LPP) to extract discriminant features and is tested and evaluated using the Yale and AR face databases.
Abstract: In this paper, an alternative formulation of orthogonal locality preserving projections (OLPP) is proposed. Schur-OLPP introduces Schur decomposition in locality preserving projections (LPP) to get the orthogonal vectors and extracts discriminant features. The proposed method was tested and evaluated using the Yale and AR face databases. Recognition rates were compared with Eigenface, Fisherface and Laplacianface. Experimental results indicated the promising performance of the proposed method.
7 citations