Intelligent Biometric Information Fusion using Support Vector Machine
01 Jan 2007-pp 325-349
About: The article was published on 2007-01-01. It has received 27 citations till now. The article focuses on the topics: Support vector machine & Biometrics.
Citations
More filters
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.
176 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•
27 Sep 2012TL;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.
59 citations
Proceedings Article•
27 Sep 2012TL;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
57 citations
Patent•
18 Sep 2012TL;DR: In this article, a local expert forest model for meta-level score fusion for event detection is proposed, where performance variations of classifiers in different regions of a score space can be adapted.
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•
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.
41 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
More filters
TL;DR: This article goes into detail about the BioID system functions, explaining the data acquisition and preprocessing techniques for voice, facial, and lip imagery data and the classification principles used for optical features and the sensor fusion options.
Abstract: Biometric identification systems, which use physical features to check a person's identity, ensure much greater security than password and number systems. Biometric features such as the face or a fingerprint can be stored on a microchip in a credit card, for example. A single feature, however, sometimes fails to be exact enough for identification. Another disadvantage of using only one feature is that the chosen feature is not always readable. Dialog Communication Systems (DCS AG) developed BioID, a multimodal identification system that uses three different features-face, voice, and lip movement-to identify people. With its three modalities, BioID achieves much greater accuracy than single-feature systems. Even if one modality is somehow disturbed-for example, if a noisy environment drowns out the voice-the ether two modalities still lead to an accurate identification. This article goes into detail about the system functions, explaining the data acquisition and preprocessing techniques for voice, facial, and lip imagery data. The authors also explain the classification principles used for optical features and the sensor fusion options (the combinations of the three results-face, voice, lip movement-to obtain varying levels of security).
386 citations
"Intelligent Biometric Information F..." refers background in this paper
...Many researchers claim that when two or more biometric information is combined, recognition accuracy increases [1] - [ 23 ]....
[...]
TL;DR: This work proposes to evaluate different binary classification schemes (support vector machine, multilayer perceptron, C4.5 decision tree, Fisher's linear discriminant, Bayesian classifier) to carry on the fusion of experts for taking a final decision on identity authentication.
Abstract: Biometric person identity authentication is gaining more and more attention. The authentication task performed by an expert is a binary classification problem: reject or accept identity claim. Combining experts, each based on a different modality (speech, face, fingerprint, etc.), increases the performance and robustness of identity authentication systems. In this context, a key issue is the fusion of the different experts for taking a final decision (i.e., accept or reject identity claim). We propose to evaluate different binary classification schemes (support vector machine, multilayer perceptron, C4.5 decision tree, Fisher's linear discriminant, Bayesian classifier) to carry on the fusion. The experimental results show that support vector machines and Bayesian classifier achieve almost the same performances, and both outperform the other evaluated classifiers.
383 citations
"Intelligent Biometric Information F..." refers methods in this paper
...Several other researchers proposed algorithms based on Support Vector Machine (SVM) [14], fuzzy clustering [15] and radial basis neural network [6, 16 ] to fuse the information at different levels....
[...]
TL;DR: A hybrid fingerprint matching scheme that uses both minutiae and ridge flow information to represent and match fingerprints, where the entire image is taken into account while constructing the ridge feature map.
372 citations
"Intelligent Biometric Information F..." refers methods in this paper
...the two databases, SVM based learning algorithm outperforms other match score fusion algorithm [ 20 ]....
[...]
...False Rejection Rate(%) Fusion�[ 20 ] on FERET Fusion�[20] on Equinox...
[...]
...False Rejection Rate(%) Fusion�[20] on FERET Fusion�[ 20 ] on Equinox...
[...]
TL;DR: Four different fingerprint matching algorithms are combined using the proposed scheme to improve the accuracy of a fingerprint verification system and it is shown that a combination of multiple impressions or multiple fingers improves the verification performance by more than 4% and 5%, respectively.
371 citations
01 Jan 2003
TL;DR: The largest experimental study to date that investigates the comparison and combination of 2D and 3D face recognition, and to incorporate signicant time lapse between gallery and probe image acquisition, finds that 3D outperforms 2D but also has a multi-modal rank-one recognition rate that is statistically signicantly greater than either 2D or 3D alone.
Abstract: Results are presented for the largest experimental study to date that investigates the comparison and combination of 2D and 3D face recognition. To our knowledge, this is also the only such study to incorporate signicant time lapse between gallery and probe image acquisition, and to look at the effect of depth resolution. Recognition results are obtained in (1) single gallery and a single probe study, and (2) a single gallery and multiple probe study. A total of 275 subjects participated in one or more data acquisition sessions. Results are presented for gallery and probe datasets of 200 subjects imaged in both 2D and 3D, with one to thirteen weeks time lapse between gallery and probe images of a given subject yielding 951 pairs of 2D and 3D images. Using a PCA-based approach tuned separately for 2D and for 3D, we nd that 3D outperforms 2D. However, we also nd a multi-modal rank-one recognition rate of 98.5% in a single probe study and 98.8% in multi-probe study, which is statistically signicantly greater than either 2D or 3D alone.
329 citations