scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Background learning for robust face recognition with PCA in the presence of clutter

TL;DR: A new method within the framework of principal component analysis (PCA) to robustly recognize faces in the presence of clutter by learning the distribution of background patterns and it is shown how this can be done for a given test image.
Abstract: We propose a new method within the framework of principal component analysis (PCA) to robustly recognize faces in the presence of clutter. The traditional eigenface recognition (EFR) method, which is based on PCA, works quite well when the input test patterns are faces. However, when confronted with the more general task of recognizing faces appearing against a background, the performance of the EFR method can be quite poor. It may miss faces completely or may wrongly associate many of the background image patterns to faces in the training set. In order to improve performance in the presence of background, we argue in favor of learning the distribution of background patterns and show how this can be done for a given test image. An eigenbackground space is constructed corresponding to the given test image and this space in conjunction with the eigenface space is used to impart robustness. A suitable classifier is derived to distinguish nonface patterns from faces. When tested on images depicting face recognition in real situations against cluttered background, the performance of the proposed method is quite good with fewer false alarms.
Citations
More filters
Journal ArticleDOI
TL;DR: A new scheme for cluster generation and classification of preceding vehicles from images and the superior performance of the proposed scheme is clearly illustrated through the classification results.
Abstract: This study presents a new scheme for cluster generation and classification of preceding vehicles from images. The proposed clustering algorithm models the distribution of vehicle images using ‘vehicle’ clusters. ‘Non-vehicle’ clusters are generated by modelling the distribution of non-vehicle images. The clusters are created using K-means clustering algorithm. Hierarchically related nested eigenspaces are acquired to reassign the patterns of each cluster. An appropriate classifier is obtained to classify the vehicles based on the ‘distance-from-feature-space’ measurement. The eigenspaces of vehicle clusters together with non-vehicle clusters are used for classification. The approach of modelling the distribution of vehicle and non-vehicle images and the choice of the classifier used are investigated through experiments thoroughly. Comparison on the performance of the proposed scheme is made with that of MultiClustered Modified Quadratic Discriminant Function approach of categorising the preceding vehicles. The superior performance of the proposed scheme is clearly illustrated through the classification results.

4 citations

Proceedings ArticleDOI
01 Dec 2015
TL;DR: The algorithm proposed intends to identify the genetically similar faces and the performance of algorithm shows that PCA is effective in extracting the features for genetic face recognition.
Abstract: Face recognition plays an important role in Image processing, especially in the field of security authentication. It is used for authenticating a person in applications like security systems and identity verification. The challenge in implementation of face recognition is to tolerate the local variations in the facial expressions of an individual. There are several approaches for face recognition, of which Principal Component Analysis (PCA) is an effective algorithm. The importance of PCA lies, not only in reducing the dimensionality of the image, but, also in finding the significant features of the image. Computation of Eigen faces help in classifying the images to be genetic and non-genetic. The algorithm proposed intends to identify the genetically similar faces. The significant features are termed as Eigen faces, and they do not correspond to specific features such as eyes, nose and ears, of face. Using statistical measures the performance of algorithm shows that PCA is effective in extracting the features for genetic face recognition.

3 citations

01 Jan 2013

2 citations


Cites methods from "Background learning for robust face..."

  • ...PCA is used primarily for both dimension reduction or pattern recognition [35-38]....

    [...]

Proceedings ArticleDOI
31 Dec 2009
TL;DR: This paper has presented a multilinear algebraic framework for fingerprint image recognition, which employs a tensor (N-mode) extension of the conventional matrix SVD, and introduced a multILinear projection algorithm for fingerprint recognition.
Abstract: Motivated by the reported out performance in the fingerprint recognition thesises of PCA by ICA in the linear case where only a single factor is allowed to vary, and the outperformance of PCA by FET when multiple factors are allowed to vary, it is natural to ask whether there a multilinear generalization of ICA and if its performance is better than the other two methods. In this paper, We have presented a multilinear algebraic framework for fingerprint image recognition, which employs a tensor (N-mode) extension of the conventional matrix SVD. We also introduced a multilinear projection algorithm for fingerprint recognition, which projects an unlabeled test image into the N constituent mode spaces to infer its mode label-sperson, finger, type

2 citations

Book ChapterDOI
Tao Gong1
28 Aug 2012
TL;DR: A novel algorithm is proposed to filter out the disturbances of PIE for face recognition that is designed with immune memory to maximize the success possibility for recognizing the faces.
Abstract: Face recognition algorithms often have to filter out the disturbances of some conditional factors such as facial pose, illumination, and expression (PIE). So an increasing number of researchers have been figuring out the best discrimi-nant transformation in the feature space of faces to improve the recognition performance. They have also proposed novel feature-matching algorithms to minimize the PIE effects. For example, Chen et al. designed a nearest feature space (NFS) embedding algorithm that outperformed the other algorithms for face recognition. By searching the most similar sample with immune learning, in this paper, a novel algorithm is proposed to filter out the disturbances of PIE for face recognition. The adaptive adjustment for filtering out the disturbance of PIE is designed with immune memory to maximize the success possibility for recognizing the faces. The clonal selection frame is used to search the most similar samples to the target face, and the selected antibodies are memorized as the candidates for the best solution or the second optimal solution. The proposed approach is evaluated on several benchmark databases and is compared with the NFS embedding algorithm. The experimental results show that the proposed approach outperforms the NFS embedding algorithm.

1 citations


Cites background from "Background learning for robust face..."

  • ...built an eigen-background space for background learning [12]....

    [...]

References
More filters
Journal ArticleDOI
TL;DR: A near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals, and that is easy to implement using a neural network architecture.
Abstract: We have developed a near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals. The computational approach taken in this system is motivated by both physiology and information theory, as well as by the practical requirements of near-real-time performance and accuracy. Our approach treats the face recognition problem as an intrinsically two-dimensional (2-D) recognition problem rather than requiring recovery of three-dimensional geometry, taking advantage of the fact that faces are normally upright and thus may be described by a small set of 2-D characteristic views. The system functions by projecting face images onto a feature space that spans the significant variations among known face images. The significant features are known as "eigenfaces," because they are the eigenvectors (principal components) of the set of faces; they do not necessarily correspond to features such as eyes, ears, and noses. The projection operation characterizes an individual face by a weighted sum of the eigenface features, and so to recognize a particular face it is necessary only to compare these weights to those of known individuals. Some particular advantages of our approach are that it provides for the ability to learn and later recognize new faces in an unsupervised manner, and that it is easy to implement using a neural network architecture.

14,562 citations

Book
01 Jan 1973
TL;DR: In this article, a unified, comprehensive and up-to-date treatment of both statistical and descriptive methods for pattern recognition is provided, including Bayesian decision theory, supervised and unsupervised learning, nonparametric techniques, discriminant analysis, clustering, preprosessing of pictorial data, spatial filtering, shape description techniques, perspective transformations, projective invariants, linguistic procedures, and artificial intelligence techniques for scene analysis.
Abstract: Provides a unified, comprehensive and up-to-date treatment of both statistical and descriptive methods for pattern recognition. The topics treated include Bayesian decision theory, supervised and unsupervised learning, nonparametric techniques, discriminant analysis, clustering, preprosessing of pictorial data, spatial filtering, shape description techniques, perspective transformations, projective invariants, linguistic procedures, and artificial intelligence techniques for scene analysis.

13,647 citations

Journal ArticleDOI
TL;DR: A face recognition algorithm which is insensitive to large variation in lighting direction and facial expression is developed, based on Fisher's linear discriminant and produces well separated classes in a low-dimensional subspace, even under severe variations in lighting and facial expressions.
Abstract: We develop a face recognition algorithm which is insensitive to large variation in lighting direction and facial expression. Taking a pattern classification approach, we consider each pixel in an image as a coordinate in a high-dimensional space. We take advantage of the observation that the images of a particular face, under varying illumination but fixed pose, lie in a 3D linear subspace of the high dimensional image space-if the face is a Lambertian surface without shadowing. However, since faces are not truly Lambertian surfaces and do indeed produce self-shadowing, images will deviate from this linear subspace. Rather than explicitly modeling this deviation, we linearly project the image into a subspace in a manner which discounts those regions of the face with large deviation. Our projection method is based on Fisher's linear discriminant and produces well separated classes in a low-dimensional subspace, even under severe variation in lighting and facial expressions. The eigenface technique, another method based on linearly projecting the image space to a low dimensional subspace, has similar computational requirements. Yet, extensive experimental results demonstrate that the proposed "Fisherface" method has error rates that are lower than those of the eigenface technique for tests on the Harvard and Yale face databases.

11,674 citations

Book
01 Jan 1972
TL;DR: This completely revised second edition presents an introduction to statistical pattern recognition, which is appropriate as a text for introductory courses in pattern recognition and as a reference book for workers in the field.
Abstract: This completely revised second edition presents an introduction to statistical pattern recognition Pattern recognition in general covers a wide range of problems: it is applied to engineering problems, such as character readers and wave form analysis as well as to brain modeling in biology and psychology Statistical decision and estimation, which are the main subjects of this book, are regarded as fundamental to the study of pattern recognition This book is appropriate as a text for introductory courses in pattern recognition and as a reference book for workers in the field Each chapter contains computer projects as well as exercises

10,526 citations