Pub Date : 2011-11-01DOI: 10.1109/BIOMS.2011.6052385
M. H. Bahari, H. V. hamme
In many criminal cases, evidence might be in the form of telephone conversations or tape recordings. Therefore, law enforcement agencies have been concerned about accurate methods to profile different characteristics of a speaker from recorded voice patterns, which facilitate the identification of a criminal. This paper proposes a new approach for speaker gender detection and age estimation, based on a hybrid architecture of Weighted Supervised Non-Negative Matrix Factorization (WSNMF) and General Regression Neural Network (GRNN). Evaluation results on a corpus of read and spontaneous speech in Dutch confirms the effectiveness of the proposed scheme.
{"title":"Speaker age estimation and gender detection based on supervised Non-Negative Matrix Factorization","authors":"M. H. Bahari, H. V. hamme","doi":"10.1109/BIOMS.2011.6052385","DOIUrl":"https://doi.org/10.1109/BIOMS.2011.6052385","url":null,"abstract":"In many criminal cases, evidence might be in the form of telephone conversations or tape recordings. Therefore, law enforcement agencies have been concerned about accurate methods to profile different characteristics of a speaker from recorded voice patterns, which facilitate the identification of a criminal. This paper proposes a new approach for speaker gender detection and age estimation, based on a hybrid architecture of Weighted Supervised Non-Negative Matrix Factorization (WSNMF) and General Regression Neural Network (GRNN). Evaluation results on a corpus of read and spontaneous speech in Dutch confirms the effectiveness of the proposed scheme.","PeriodicalId":129267,"journal":{"name":"2011 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BIOMS)","volume":"332 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134502910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-11-01DOI: 10.1109/BIOMS.2011.6053681
Daniel Hartung
Currently biometric systems are evaluated using performance measures like the Equal Error Rate in database comparisons. The biometric performance can give an indication how good a certain system is suited to handle the biometric samples. However, there are more factors of reasoning: test data and simulations are always limited and the performance does not give any insight in how discriminating the features from a certain source are in theory. In this paper we propose a model for vein skeletons and an entropy estimator on the skeletonized representation of the vein patterns to overcome the before mentioned limitations. The results are compared to information theoretical entropy estimations on a specific finger vein database.
{"title":"Entropy estimator and formal model for vascular skeletons","authors":"Daniel Hartung","doi":"10.1109/BIOMS.2011.6053681","DOIUrl":"https://doi.org/10.1109/BIOMS.2011.6053681","url":null,"abstract":"Currently biometric systems are evaluated using performance measures like the Equal Error Rate in database comparisons. The biometric performance can give an indication how good a certain system is suited to handle the biometric samples. However, there are more factors of reasoning: test data and simulations are always limited and the performance does not give any insight in how discriminating the features from a certain source are in theory. In this paper we propose a model for vein skeletons and an entropy estimator on the skeletonized representation of the vein patterns to overcome the before mentioned limitations. The results are compared to information theoretical entropy estimations on a specific finger vein database.","PeriodicalId":129267,"journal":{"name":"2011 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BIOMS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125283465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-11-01DOI: 10.1109/BIOMS.2011.6053684
R. D. Labati, A. Genovese, V. Piuri, F. Scotti
Current contactless fingertip recognition systems based on three-dimensional finger models mostly use multiple views (N > 2) or structured light illumination with multiple patterns projected over a period of time. In this paper, we present a novel methodology able to obtain a fast and accurate three-dimensional reconstruction of the fingertip by using a single two-view acquisition and a static projected pattern. The acquisition setup is less constrained than the ones proposed in the literature and requires only that the finger is placed according to the depth of focus of the cameras, and in the overlapping field of views. The obtained pairs of images are processed in order to extract the information related to the fingertip and the projected pattern. The projected pattern permits to extract a set of reference points in the two images, which are then matched by using a correlation approach. The information related to a previous calibration of the cameras is then used in order to estimate the finger model, and one input image is wrapped on the resulting three-dimensional model, obtaining a three-dimensional pattern with a limited distortion of the ridges. In order to obtain data that can be treated by traditional algorithms, the obtained three-dimensional models are then unwrapped into bidimensional images. The quality of the unwrapped images is evaluated by using a software designed for contact-based fingerprint images. The obtained results show that the methodology is feasible and a realistic three-dimensional reconstruction can be achieved with few constraints. These results also show that the fingertip models computed by using our approach can be processed by both specific three-dimensional matching algorithms and traditional matching approaches. We also compared the results with the ones obtained without using structured light techniques, showing that the use of a projector achieves a faster and more accurate fingertip reconstruction.
{"title":"Fast 3-D fingertip reconstruction using a single two-view structured light acquisition","authors":"R. D. Labati, A. Genovese, V. Piuri, F. Scotti","doi":"10.1109/BIOMS.2011.6053684","DOIUrl":"https://doi.org/10.1109/BIOMS.2011.6053684","url":null,"abstract":"Current contactless fingertip recognition systems based on three-dimensional finger models mostly use multiple views (N > 2) or structured light illumination with multiple patterns projected over a period of time. In this paper, we present a novel methodology able to obtain a fast and accurate three-dimensional reconstruction of the fingertip by using a single two-view acquisition and a static projected pattern. The acquisition setup is less constrained than the ones proposed in the literature and requires only that the finger is placed according to the depth of focus of the cameras, and in the overlapping field of views. The obtained pairs of images are processed in order to extract the information related to the fingertip and the projected pattern. The projected pattern permits to extract a set of reference points in the two images, which are then matched by using a correlation approach. The information related to a previous calibration of the cameras is then used in order to estimate the finger model, and one input image is wrapped on the resulting three-dimensional model, obtaining a three-dimensional pattern with a limited distortion of the ridges. In order to obtain data that can be treated by traditional algorithms, the obtained three-dimensional models are then unwrapped into bidimensional images. The quality of the unwrapped images is evaluated by using a software designed for contact-based fingerprint images. The obtained results show that the methodology is feasible and a realistic three-dimensional reconstruction can be achieved with few constraints. These results also show that the fingertip models computed by using our approach can be processed by both specific three-dimensional matching algorithms and traditional matching approaches. We also compared the results with the ones obtained without using structured light techniques, showing that the use of a projector achieves a faster and more accurate fingertip reconstruction.","PeriodicalId":129267,"journal":{"name":"2011 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BIOMS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134542256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-11-01DOI: 10.1109/BIOMS.2011.6052380
Nelson C. Francisco, A. Zaghetto, B. Macchiavello, E. Silva, M. Lima-Marques, Nuno M. M. Rodrigues, S. Faria
Recently, touchless multiview fingerprinting technology has been proposed as an alternative to overcome the intrinsic problems of traditional contact-based systems. Nevertheless, compression of this kind of signal has not been fully evaluated and standardized. This paper investigates the comparative performance of several encoders for this data, namely WSQ, JPEG2000, H.264/AVC and MMP. Experimental results show that WSQ encoder, which is the current compression standard for contact-based fingerprints, is objectively outperformed by all others. In particular, MMP, which achieved the best results, outperforms WSQ by up to 4 dB.
{"title":"Compression of touchless multiview fingerprints","authors":"Nelson C. Francisco, A. Zaghetto, B. Macchiavello, E. Silva, M. Lima-Marques, Nuno M. M. Rodrigues, S. Faria","doi":"10.1109/BIOMS.2011.6052380","DOIUrl":"https://doi.org/10.1109/BIOMS.2011.6052380","url":null,"abstract":"Recently, touchless multiview fingerprinting technology has been proposed as an alternative to overcome the intrinsic problems of traditional contact-based systems. Nevertheless, compression of this kind of signal has not been fully evaluated and standardized. This paper investigates the comparative performance of several encoders for this data, namely WSQ, JPEG2000, H.264/AVC and MMP. Experimental results show that WSQ encoder, which is the current compression standard for contact-based fingerprints, is objectively outperformed by all others. In particular, MMP, which achieved the best results, outperforms WSQ by up to 4 dB.","PeriodicalId":129267,"journal":{"name":"2011 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BIOMS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127567404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-11-01DOI: 10.1109/BIOMS.2011.6052384
Breno Santos de Araújo, A. Machado
Automatic face recognition systems have currently reached high hit rates. Nevertheless, simple steps like image registration are not being considered in several methods. The alignment of the set of images in a same coordinated system must be seen as an initial and crucial step in algorithms that are based on dimensionality reduction. This work aims at analyzing the importance of registration as a preprocessing step in recognition algorithms based on eigen decomposition. A set of experiments was conducted, in which images of publicly available databases were processed under rotation and translation. These operations put the images on controlled non-registered form for precise evaluation of three recognition methods — Principal Component Analysis, Two-dimensional Principal Component Analysis and FisherFaces, combined with the Euclidean distance and cosine similarity measurements. The experiments revealed the best combination of methods. Moreover, the behavior of hit rate with respect to rotation and translation misalignments were characterized as a Gaussian function.
{"title":"Towards a better comprehension of the role of image registration in face recognition algorithms","authors":"Breno Santos de Araújo, A. Machado","doi":"10.1109/BIOMS.2011.6052384","DOIUrl":"https://doi.org/10.1109/BIOMS.2011.6052384","url":null,"abstract":"Automatic face recognition systems have currently reached high hit rates. Nevertheless, simple steps like image registration are not being considered in several methods. The alignment of the set of images in a same coordinated system must be seen as an initial and crucial step in algorithms that are based on dimensionality reduction. This work aims at analyzing the importance of registration as a preprocessing step in recognition algorithms based on eigen decomposition. A set of experiments was conducted, in which images of publicly available databases were processed under rotation and translation. These operations put the images on controlled non-registered form for precise evaluation of three recognition methods — Principal Component Analysis, Two-dimensional Principal Component Analysis and FisherFaces, combined with the Euclidean distance and cosine similarity measurements. The experiments revealed the best combination of methods. Moreover, the behavior of hit rate with respect to rotation and translation misalignments were characterized as a Gaussian function.","PeriodicalId":129267,"journal":{"name":"2011 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BIOMS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116500851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-11-01DOI: 10.1109/BIOMS.2011.6052381
M. De Marsico, M. Nappi, D. Riccio
In this work we present FOVEA, a system for video sequence indexing based on the identity of appearing subjects. We will detail the features of the single component modules, devoting special attention to classification and clustering. The system presents a number of peculiarities that distinguish it from existing ones. Among these, the account for the concomitant appearance of two subjects in the same clip, and the use of such information in the process of identity mapping. FOVEA was tested on 16 video clips with results that assess both its efficacy and efficiency.
{"title":"FOVEA: A video frame organizer via identity extraction and analysis","authors":"M. De Marsico, M. Nappi, D. Riccio","doi":"10.1109/BIOMS.2011.6052381","DOIUrl":"https://doi.org/10.1109/BIOMS.2011.6052381","url":null,"abstract":"In this work we present FOVEA, a system for video sequence indexing based on the identity of appearing subjects. We will detail the features of the single component modules, devoting special attention to classification and clustering. The system presents a number of peculiarities that distinguish it from existing ones. Among these, the account for the concomitant appearance of two subjects in the same clip, and the use of such information in the process of identity mapping. FOVEA was tested on 16 video clips with results that assess both its efficacy and efficiency.","PeriodicalId":129267,"journal":{"name":"2011 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BIOMS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120988906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-11-01DOI: 10.1109/BIOMS.2011.6052382
S. Safie, J. Soraghan, L. Petropoulakis
This paper presents a new feature extraction method known as Pulse Active Width (PAW) implemented on electrocardiogram (ECG) for biometric authentication. This method is developed based on the concept of Pulse Width Modulation (PWM). A total of 196 ECGs from 98 subjects, taken from the Physikalisch-Technische Bundesanstalt (PTB) database are used in the simulations. Biometric performance profile such as the area under ROC (AUR) and equal error rate (EER) are then used to evaluate the results. It is shown that the PAW method outperforms conventional temporal feature extraction techniques.
{"title":"ECG biometric authentication using Pulse Active Width (PAW)","authors":"S. Safie, J. Soraghan, L. Petropoulakis","doi":"10.1109/BIOMS.2011.6052382","DOIUrl":"https://doi.org/10.1109/BIOMS.2011.6052382","url":null,"abstract":"This paper presents a new feature extraction method known as Pulse Active Width (PAW) implemented on electrocardiogram (ECG) for biometric authentication. This method is developed based on the concept of Pulse Width Modulation (PWM). A total of 196 ECGs from 98 subjects, taken from the Physikalisch-Technische Bundesanstalt (PTB) database are used in the simulations. Biometric performance profile such as the area under ROC (AUR) and equal error rate (EER) are then used to evaluate the results. It is shown that the PAW method outperforms conventional temporal feature extraction techniques.","PeriodicalId":129267,"journal":{"name":"2011 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BIOMS)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117346974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-11-01DOI: 10.1109/BIOMS.2011.6053683
Emanuela Marasco, Carlo Sansone
Multimodal biometric systems integrate information from multiple sources to improve the performance of a typical unimodal biometric system. The use of multimodal biometric systems has been encouraged by the threat of spoofing, where an impostor fakes a biometric trait. The reason lies on the assumption that, an impostor must fake all the fused modalities to be accepted. Recent studies showed that, there is a vulnerability of the existing fusion schemes in presence of attacks where only a subset of the fused modalities is spoofed. Among the possible information fusion approaches, recently, a framework for the optimal combination of match scores that is based on the likelihood ratio (LR) test has been presented. It is based on the modeling of the distributions of genuine and impostor match scores as a finite Gaussian mixture models. Since standard LR test demonstrated to be very sensitive to spoofing attacks, in this paper we analyze the robustness of a voting strategy based on likelihood ratio test in the presence of spoofing. The analysis has been carried out on the Biosecure multimodal database, demonstrating the advantages of a voting strategy with respect to the standard LR approach.
{"title":"On the security evaluation of a multibiometric system based on a voting strategy involving likelihood ratio statistic tests","authors":"Emanuela Marasco, Carlo Sansone","doi":"10.1109/BIOMS.2011.6053683","DOIUrl":"https://doi.org/10.1109/BIOMS.2011.6053683","url":null,"abstract":"Multimodal biometric systems integrate information from multiple sources to improve the performance of a typical unimodal biometric system. The use of multimodal biometric systems has been encouraged by the threat of spoofing, where an impostor fakes a biometric trait. The reason lies on the assumption that, an impostor must fake all the fused modalities to be accepted. Recent studies showed that, there is a vulnerability of the existing fusion schemes in presence of attacks where only a subset of the fused modalities is spoofed. Among the possible information fusion approaches, recently, a framework for the optimal combination of match scores that is based on the likelihood ratio (LR) test has been presented. It is based on the modeling of the distributions of genuine and impostor match scores as a finite Gaussian mixture models. Since standard LR test demonstrated to be very sensitive to spoofing attacks, in this paper we analyze the robustness of a voting strategy based on likelihood ratio test in the presence of spoofing. The analysis has been carried out on the Biosecure multimodal database, demonstrating the advantages of a voting strategy with respect to the standard LR approach.","PeriodicalId":129267,"journal":{"name":"2011 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BIOMS)","volume":"213 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115211228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-11-01DOI: 10.1109/BIOMS.2011.6053682
Z. Akhtar, B. Biggio, G. Fumera, G. Marcialis
Spoof attacks consist in submitting fake biometric traits to biometric systems, and are a major threat that can curtail their security. Multi-modal biometric systems are commonly believed to be intrinsically more robust to spoof attacks, but recent works have shown that they can be evaded by spoofing even a single biometric trait. This result was however obtained under the worst-case scenario that the attacker is able to fabricate an exact replica of the genuine biometric trait, which was simulated by assuming that the matching score distribution of fake traits is identical to the one of genuine users. This demands for a more thorough investigation of the robustness of multi-modal biometric systems against realistic spoof attacks, namely under non-worst case scenarios. In this paper we focus on bi-modal systems made up of a face and a fingerprint matcher, whose scores are fused using the well-known sum, product, weighted sum and likelihood ratio (LLR) rules. We evaluate their robustness against realistic spoof attacks obtained by fabricating fake biometric traits. The main goal of our study is to investigate whether a realistic spoof attack against both modalities can allow the attacker to crack the multimodal system. Our results show that even in a realistic, non-worst case scenario, the false acceptance rate (FAR) can remarkably increase.
{"title":"Robustness of multi-modal biometric systems under realistic spoof attacks against all traits","authors":"Z. Akhtar, B. Biggio, G. Fumera, G. Marcialis","doi":"10.1109/BIOMS.2011.6053682","DOIUrl":"https://doi.org/10.1109/BIOMS.2011.6053682","url":null,"abstract":"Spoof attacks consist in submitting fake biometric traits to biometric systems, and are a major threat that can curtail their security. Multi-modal biometric systems are commonly believed to be intrinsically more robust to spoof attacks, but recent works have shown that they can be evaded by spoofing even a single biometric trait. This result was however obtained under the worst-case scenario that the attacker is able to fabricate an exact replica of the genuine biometric trait, which was simulated by assuming that the matching score distribution of fake traits is identical to the one of genuine users. This demands for a more thorough investigation of the robustness of multi-modal biometric systems against realistic spoof attacks, namely under non-worst case scenarios. In this paper we focus on bi-modal systems made up of a face and a fingerprint matcher, whose scores are fused using the well-known sum, product, weighted sum and likelihood ratio (LLR) rules. We evaluate their robustness against realistic spoof attacks obtained by fabricating fake biometric traits. The main goal of our study is to investigate whether a realistic spoof attack against both modalities can allow the attacker to crack the multimodal system. Our results show that even in a realistic, non-worst case scenario, the false acceptance rate (FAR) can remarkably increase.","PeriodicalId":129267,"journal":{"name":"2011 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BIOMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131340199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：