Intelligent Biometric Information Fusion using Support Vector Machine

Richa Singh; Mayank Vatsa; Afzel Noore

doi:10.1007/978-3-540-38233-1_12

Book Chapter•DOI•

Intelligent Biometric Information Fusion using Support Vector Machine

Richa Singh¹, Mayank Vatsa¹, Afzel Noore¹

01 Jan 2007-pp 325-349

About: The article was published on 2007-01-01. It has received 27 citation(s) till now. The article focuses on the topic(s): Support vector machine & Biometrics.

Topics: Support vector machine (51%), Biometrics (50%)

Citations

PDF

Open Access

More filters

Journal Article•DOI•

Integrated multilevel image fusion and match score fusion of visible and infrared face images for robust face recognition

[...]

Richa Singh¹, Mayank Vatsa¹, Afzel Noore¹•Institutions (1)

01 Mar 2008-Pattern Recognition

TL;DR: An integrated image fusion and match score fusion of multispectral face images using [email protected] SVM and Dezert Smarandache theory of fusion which is based on plausible and paradoxical reasoning is presented.

Abstract: This paper presents an integrated image fusion and match score fusion of multispectral face images. The fusion of visible and long wave infrared face images is performed using [email protected] SVM which uses multiple SVMs to learn both the local and global properties of the multispectral face images at different granularity levels and resolution. The [email protected] performs accurate classification which is subsequently used to dynamically compute the weights of visible and infrared images for generating a fused face image. 2D log polar Gabor transform and local binary pattern feature extraction algorithms are applied to the fused face image to extract global and local facial features, respectively. The corresponding match scores are fused using Dezert Smarandache theory of fusion which is based on plausible and paradoxical reasoning. The efficacy of the proposed algorithm is validated using the Notre Dame and Equinox databases and is compared with existing statistical, learning, and evidence theory based fusion algorithms.

151 citations

Cites background or methods from "Intelligent Biometric Information F..."

...In our previous research [12], we used 2ν-SVM for feature fusion, match score fusion, and expert fusion....
[...]
...Further, several fusion algorithms have been proposed to fuse the information extracted from visible and LWIR face images at image level [8], [9], [10], [11], feature level [10], [11], [12], match score level [12], and decision level [12]....
[...]

Proceedings Article•

EEG biometrics for individual recognition in resting state with closed eyes

[...]

Daria La Rocca¹, Patrizio Campisi¹, G. Scarano²•Institutions (2)

27 Sep 2012-

TL;DR: The resting state with closed eyes acquisition protocol has been here used and deeply investigated by varying the employed electrodes configuration both in number and location for optimizing the recognition performance still guaranteeing sufficient user convenience.

Abstract: In this paper EEG signals are employed for the purpose of automatic user recognition. Specifically the resting state with closed eyes acquisition protocol has been here used and deeply investigated by varying the employed electrodes configuration both in number and location for optimizing the recognition performance still guaranteeing sufficient user convenience. A database of 45 healthy subjects has been employed in the analysis. Autoregressive stochastic modeling and polynomial regression based classification has been applied to extracted brain rhythms in order to identify the most distinctive contributions of the different subbands in the recognition process. Our analysis has shown that significantly high recognition rates, up to 98.73%, can be achievedwhen using proper triplets of electrodes,which cannot be achieved by employing couple of electrodes,whereas sets of five electrodes in the central posterior region of the scalp can guarantee very high recognition performance while limiting user convenience.

58 citations

Proceedings Article•

Forensic biometrics: From two communities to one discipline

[...]

Didier Meuwly¹, Raymond N.J. Veldhuis²•Institutions (2)

27 Sep 2012-

TL;DR: How the fields of biometrics and forensic science can contribute and benefit from each other is described to foster the development of new methods and tools improving the current forensic biometric applications and allowing for the creation of new ones.

Abstract: This article describes how the fields of biometrics and forensic science can contribute and benefit from each other. The aim is to foster the development of new methods and tools improving the current forensic biometric applications and allowing for the creation of new ones. The article begins with a definition and a summary of the development in forensic biometrics. Then it describes the data and biometric modalities of interest in forensic science and the forensic applications embedding biometric technology. On this basis it describes the solutions and limitations of the current practice regarding the data, the technology and the inference models. Finally, it proposes research orientations for the improvement of the current forensic biometric applications and suggests some ideas for the development of some new forensic biometric applications

56 citations

Patent•

Score fusion and training data recycling for video classification

[...]

Jingchen Liu¹, Scott McCloskey¹•Institutions (1)

18 Sep 2012-

Abstract: Multiple classifiers can be applied independently to evaluate images or video. Where there are heavily imbalanced class distributions, a local expert forest model for meta-level score fusion for event detection can be used. Performance variations of classifiers in different regions of a score space can be adapted. Multiple pairs of experts based on different partitions, or “trees,” can form a “forest,” balancing local adaptivity and over-fitting. Among ensemble learning methods, stacking with a meta-level classifier can be used to fuse an output of multiple base-level classifiers to generate a final score. A knowledge-transfer framework can reutilize the base-training data for learning the meta-level classifier. By recycling the knowledge obtained during a base-classifier-training stage, efficient use can be made of all available information, such as can be used to achieve better fusion and better overall performance.

43 citations

Posted Content•

Unification of Evidence Theoretic Fusion Algorithms: A Case Study in Level-2 and Level-3 Fingerprint Features

[...]

Mayank Vatsa¹, Richa Singh¹, Afzel Noore¹•Institutions (1)

01 Jun 2017-viXra

TL;DR: This paper formulates an evidence-theoretic multimodal unification approach using belief functions that take into account the variability in biometric image characteristics that is computationally efficient, and the verification accuracy is not compromised even when conflicting decisions are encountered.

Abstract: This paper formulates an evidence-theoretic multimodal unification approach using belief functions that takes into account the variability in biometric image characteristics. While processing non-ideal images the variation in the quality of features at different levels of abstraction may cause individual classifiers to generate conflicting genuine-impostor decisions.

40 citations

Cites background or methods from "Intelligent Biometric Information F..."

...In our previous research [5], we found that for multimodal fusion, 2ν-SVM provides better classification with lower time complexity compared to the classical SVM [20]....
[...]
...Thus, verification based on unimodal biometric systems is not always reliable, and researchers have shown that the fusion of multiple biometric modalities generally provides higher verification performance [2]–[5]....
[...]
...Existing biometric fusion algorithms such as sum rule [4] and support vector machine (SVM) fusion [5] yield good performance for some applications or under certain conditions but not universally for all scenarios....
[...]
...In the literature, there are different forms of biometric information fusion [2], [4], [5]: single biometric–multiple representation, single biometric– multiple matchers, multiple biometrics–multiple representa-...
[...]

References

PDF

Open Access

More filters

Book•

The Nature of Statistical Learning Theory

[...]

Vladimir Vapnik¹•Institutions (1)

01 Jan 1995-

TL;DR: Setting of the learning problem consistency of learning processes bounds on the rate of convergence ofLearning processes controlling the generalization ability of learning process constructing learning algorithms what is important in learning theory?

Abstract: Setting of the learning problem consistency of learning processes bounds on the rate of convergence of learning processes controlling the generalization ability of learning processes constructing learning algorithms what is important in learning theory?.

38,164 citations

"Intelligent Biometric Information F..." refers background or methods in this paper

...and C is the factor used to control the violation of safety margin rule [ 33 ]....
[...]
...Support Vector Machine, proposed by [ 33 ], is a powerful methodology for solving problems in nonlinear classification, function estimation and density 330 R. Singh et al....
[...]

Journal Article•DOI•

Eigenfaces vs. Fisherfaces: recognition using class specific linear projection

[...]

Peter N. Belhumeur¹, Joao P. Hespanha¹, David J. Kriegman¹•Institutions (1)

01 Jul 1997-IEEE Transactions on Pattern Analysis and Machine Intelligence

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

"Intelligent Biometric Information F..." refers methods in this paper

...These plots show that the performance of both the phase and amplitude features are comparable and they outperform the standard PCA and LDA based face recognition algorithms [ 46 ]....
[...]

Journal Article•DOI•

On combining classifiers

[...]

Josef Kittler¹, M. Hatef², Robert P. W. Duin³, Jiri Matas¹•Institutions (3)

01 Mar 1998-IEEE Transactions on Pattern Analysis and Machine Intelligence

TL;DR: A common theoretical framework for combining classifiers which use distinct pattern representations is developed and it is shown that many existing schemes can be considered as special cases of compound classification where all the pattern representations are used jointly to make a decision.

Abstract: We develop a common theoretical framework for combining classifiers which use distinct pattern representations and show that many existing schemes can be considered as special cases of compound classification where all the pattern representations are used jointly to make a decision. An experimental comparison of various classifier combination schemes demonstrates that the combination rule developed under the most restrictive assumptions-the sum rule-outperforms other classifier combinations schemes. A sensitivity analysis of the various schemes to estimation errors is carried out to show that this finding can be justified theoretically.

5,535 citations

"Intelligent Biometric Information F..." refers background or methods or result in this paper

...In [ 1 ], Kittler proposed a set of matching score fusion rules to combine the classifier which includes majority voting, sum rule, and product rule....
[...]
...Here the parameter C is replaced by another parameter ν� [0, 1 ] which is the lower bound on the fraction of support vectors and upper bound on the number of fraction of margin errors....
[...]
...Many researchers claim that when two or more biometric information is combined, recognition accuracy increases [ 1 ] - [23]....
[...]
...It has been suggested that the fusion of match scores of two or more classifiers gives better performance over a single classifier [ 1 , 2]. In general, match score fusion is performed using sum rule, product rule or other statistical rules....
[...]
...This plot also compares the results with min/max rule based expert fusion [ 1 ]....
[...]

Journal Article•DOI•

The FERET evaluation methodology for face-recognition algorithms

[...]

P.J. Phillips, Hyeonjoon Moon, Syed A. Rizvi¹, Patrick J. Rauss²•Institutions (2)

01 Oct 2000-IEEE Transactions on Pattern Analysis and Machine Intelligence

TL;DR: Two of the most critical requirements in support of producing reliable face-recognition systems are a large database of facial images and a testing procedure to evaluate systems.

Abstract: Two of the most critical requirements in support of producing reliable face-recognition systems are a large database of facial images and a testing procedure to evaluate systems. The Face Recognition Technology (FERET) program has addressed both issues through the FERET database of facial images and the establishment of the FERET tests. To date, 14,126 images from 1,199 individuals are included in the FERET database, which is divided into development and sequestered portions of the database. In September 1996, the FERET program administered the third in a series of FERET face-recognition tests. The primary objectives of the third test were to 1) assess the state of the art, 2) identify future areas of research, and 3) measure algorithm performance.

4,690 citations

"Intelligent Biometric Information F..." refers methods in this paper

...To study the performance of various levels of fusion, experiments are performed using two face databases: • Frontal face images from the colored FERET database [ 43 ]....
[...]

Journal Article•DOI•

New Support Vector Algorithms

[...]

Bernhard Schölkopf¹, Alexander J. Smola², Robert C. Williamson², Peter L. Bartlett²•Institutions (2)

01 May 2000-Neural Computation

TL;DR: A new class of support vector algorithms for regression and classification that eliminates one of the other free parameters of the algorithm: the accuracy parameter in the regression case, and the regularization constant C in the classification case.

Abstract: We propose a new class of support vector algorithms for regression and classification. In these algorithms, a parameter ν lets one effectively control the number of support vectors. While this can be useful in its own right, the parameterization has the additional benefit of enabling us to eliminate one of the other free parameters of the algorithm: the accuracy parameter epsilon in the regression case, and the regularization constant C in the classification case. We describe the algorithms, give some theoretical results concerning the meaning and the choice of ν, and report experimental results.

2,531 citations

"Intelligent Biometric Information F..." refers methods in this paper

...One alternative and intuitive approach to solve this problem is the use of ν-SVM of a soft margin variant of the optimal hyperplane which uses the ν-parameterization [ 35 ] and [36]....
[...]