Pub Date : 2010-10-25DOI: 10.1109/BIOMS.2010.5610441
F. Beritelli, Andrea Spadaccini
This paper presents a performance evaluation of a speech biometry system based on the statistical models GMM (Gaussian Mixture Models). In particular, the paper underlines the robustness to the degradation of various natural noises, and their impact on the system. Finally, the impact of the duration to both training and test sequences is highlighted. Results show that the noise can have the impact on the degradation of the performance (see EER values) which vary from 100 % to 300 % on the basis of the type of noise which depends on only one of two compared sequences. The duration of the sequences is a very important parameter, mostly for training phase, for which it is necessary to have at least 25 seconds long talk.
{"title":"Performance evaluation of an automatic forensic speaker recognition system based on GMM","authors":"F. Beritelli, Andrea Spadaccini","doi":"10.1109/BIOMS.2010.5610441","DOIUrl":"https://doi.org/10.1109/BIOMS.2010.5610441","url":null,"abstract":"This paper presents a performance evaluation of a speech biometry system based on the statistical models GMM (Gaussian Mixture Models). In particular, the paper underlines the robustness to the degradation of various natural noises, and their impact on the system. Finally, the impact of the duration to both training and test sequences is highlighted. Results show that the noise can have the impact on the degradation of the performance (see EER values) which vary from 100 % to 300 % on the basis of the type of noise which depends on only one of two compared sequences. The duration of the sequences is a very important parameter, mostly for training phase, for which it is necessary to have at least 25 seconds long talk.","PeriodicalId":179925,"journal":{"name":"2010 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115004032","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 : 2010-10-25DOI: 10.1109/BIOMS.2010.5610445
T. Bianchi, Stefano Turchi, A. Piva, Ruggero Donida Labati, V. Piuri, F. Scotti
In this paper, we address the problem of FingerCode-based identity matching using encrypted templates. Instead of the classical approach of combining secure signal processing (SSP) tools to mimic the behavior of some well-known identity matching algorithm, we will investigate the possibility of using a SSP-friendly biometric implementation, i.e., an implementation based on SSP tools. We will propose two alternative strategies for reducing the size of the FingerCode templates, to make them compatible with existing SSP solutions. Experimental results show that feature size reduction has a very limited impact on the accuracy of the biometric system, demonstrating that encrypted domain identity matching can be implemented without sacrificing biometric performance.
{"title":"Implementing FingerCode-based identity matching in the encrypted domain","authors":"T. Bianchi, Stefano Turchi, A. Piva, Ruggero Donida Labati, V. Piuri, F. Scotti","doi":"10.1109/BIOMS.2010.5610445","DOIUrl":"https://doi.org/10.1109/BIOMS.2010.5610445","url":null,"abstract":"In this paper, we address the problem of FingerCode-based identity matching using encrypted templates. Instead of the classical approach of combining secure signal processing (SSP) tools to mimic the behavior of some well-known identity matching algorithm, we will investigate the possibility of using a SSP-friendly biometric implementation, i.e., an implementation based on SSP tools. We will propose two alternative strategies for reducing the size of the FingerCode templates, to make them compatible with existing SSP solutions. Experimental results show that feature size reduction has a very limited impact on the accuracy of the biometric system, demonstrating that encrypted domain identity matching can be implemented without sacrificing biometric performance.","PeriodicalId":179925,"journal":{"name":"2010 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126004097","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 : 2010-10-25DOI: 10.1109/BIOMS.2010.5610443
Gissel Zamonsky Pedernera, Sebastian Sznur, Gustavo Sorondo Ovando, S. García, G. Meschino
Keystroke dynamics is a set of computer techniques that has been used successfully for many years for authentication mechanisms and masqueraders detection. Classification algorithms have reportedly performed well, but there is room for improvement. As obtaining real intruders keystrokes is a very difficult task, it has been a common practice to use normal users to capture keystroke data in previous work. Our research presents a novel approach to intruder classification using real intrusion datasets and focusing on intruders behavior. We compute six distance measures between sessions to cluster them using both modified K-means and Subtractive Clustering algorithms. Our distance measures use features that came from the relation between intruders sessions, instead of using features from each user only. The performance evaluation of our experiments showed that results are promising and intruders can be successfully classified with acceptable error rates.
{"title":"Revisiting clustering methods to their application on keystroke dynamics for intruder classification","authors":"Gissel Zamonsky Pedernera, Sebastian Sznur, Gustavo Sorondo Ovando, S. García, G. Meschino","doi":"10.1109/BIOMS.2010.5610443","DOIUrl":"https://doi.org/10.1109/BIOMS.2010.5610443","url":null,"abstract":"Keystroke dynamics is a set of computer techniques that has been used successfully for many years for authentication mechanisms and masqueraders detection. Classification algorithms have reportedly performed well, but there is room for improvement. As obtaining real intruders keystrokes is a very difficult task, it has been a common practice to use normal users to capture keystroke data in previous work. Our research presents a novel approach to intruder classification using real intrusion datasets and focusing on intruders behavior. We compute six distance measures between sessions to cluster them using both modified K-means and Subtractive Clustering algorithms. Our distance measures use features that came from the relation between intruders sessions, instead of using features from each user only. The performance evaluation of our experiments showed that results are promising and intruders can be successfully classified with acceptable error rates.","PeriodicalId":179925,"journal":{"name":"2010 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115660936","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 : 2010-10-25DOI: 10.1109/BIOMS.2010.5610442
F. Beritelli, Andrea Spadaccini
This paper presents an evolution of a biometric identity verification system based on heart sounds. The system is built using Gaussian Mixture Models (GMMs) and uses features extracted both from the spectral domain and the time domain in order to improve the performance, measured in terms of Equal Error Rate (EER), with respect to similar systems. The best result obtained using our approach, computed over a database of 165 people, is an EER of 13,70 %, that outperforms other similar approaches.
{"title":"An improved biometric identification system based on heart sounds and Gaussian Mixture Models","authors":"F. Beritelli, Andrea Spadaccini","doi":"10.1109/BIOMS.2010.5610442","DOIUrl":"https://doi.org/10.1109/BIOMS.2010.5610442","url":null,"abstract":"This paper presents an evolution of a biometric identity verification system based on heart sounds. The system is built using Gaussian Mixture Models (GMMs) and uses features extracted both from the spectral domain and the time domain in order to improve the performance, measured in terms of Equal Error Rate (EER), with respect to similar systems. The best result obtained using our approach, computed over a database of 165 people, is an EER of 13,70 %, that outperforms other similar approaches.","PeriodicalId":179925,"journal":{"name":"2010 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114512107","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 : 2010-10-25DOI: 10.1109/BIOMS.2010.5610439
D. Impedovo, G. Pirlo
In this paper a voice biometric system for secure human computer interaction is considered. The proposed approach uses multi resolution HMM-based classifiers combined both at model- and decision-level. The different resolution representations of the speaker are obtained by considering multiple frame lengths in the feature extraction phase and from these representations a single Pseudo-Multi Parallel Branch (PMPB) Hidden Markov Model is obtained (model-level fusion). In the verification process, multiple P-MPB based classifiers are inputted with different resolution representations of the speech signal: the final decision is obtained by means of different combination techniques (decision-level fusion).
{"title":"On combining HMM-based speaker verification classifiers","authors":"D. Impedovo, G. Pirlo","doi":"10.1109/BIOMS.2010.5610439","DOIUrl":"https://doi.org/10.1109/BIOMS.2010.5610439","url":null,"abstract":"In this paper a voice biometric system for secure human computer interaction is considered. The proposed approach uses multi resolution HMM-based classifiers combined both at model- and decision-level. The different resolution representations of the speaker are obtained by considering multiple frame lengths in the feature extraction phase and from these representations a single Pseudo-Multi Parallel Branch (PMPB) Hidden Markov Model is obtained (model-level fusion). In the verification process, multiple P-MPB based classifiers are inputted with different resolution representations of the speech signal: the final decision is obtained by means of different combination techniques (decision-level fusion).","PeriodicalId":179925,"journal":{"name":"2010 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114880483","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 : 2010-10-25DOI: 10.1109/BIOMS.2010.5610444
L. Balduzzi, Giovanni Fusco, F. Odone, S. Dini, M. Mesiti, Augusto Destrero, Alberto Lovato
We present a work in progress on a face biometry system for visually impaired users - the result of a very close interaction among scientists, engineers, and a users group formed by visually impaired and social assistants. The prototype under development implements recent trends of video analysis and follows closely the suggestions given by the working group, with the ambitious goal of developing a device easy to use that can be an effective help to improve communication and inclusion of visually impaired population. The prototype works real-time processing the incoming video stream to the purpose of locating the presence of people and spotting known faces. Each event of interest produces a simple audio feedback to the user, allowing him or her to locate the presence of people before they start talking or highlighting known faces in noisy environments. So far the prototype has been quantitatively validated through a set of experiments carried out in lab; also a qualitative evaluation by a heterogeneous group of perspective users, users' relatives, social workers, and experts gave us many positive comments and useful feedbacks for future work.
{"title":"Low-cost face biometry for visually impaired users","authors":"L. Balduzzi, Giovanni Fusco, F. Odone, S. Dini, M. Mesiti, Augusto Destrero, Alberto Lovato","doi":"10.1109/BIOMS.2010.5610444","DOIUrl":"https://doi.org/10.1109/BIOMS.2010.5610444","url":null,"abstract":"We present a work in progress on a face biometry system for visually impaired users - the result of a very close interaction among scientists, engineers, and a users group formed by visually impaired and social assistants. The prototype under development implements recent trends of video analysis and follows closely the suggestions given by the working group, with the ambitious goal of developing a device easy to use that can be an effective help to improve communication and inclusion of visually impaired population. The prototype works real-time processing the incoming video stream to the purpose of locating the presence of people and spotting known faces. Each event of interest produces a simple audio feedback to the user, allowing him or her to locate the presence of people before they start talking or highlighting known faces in noisy environments. So far the prototype has been quantitatively validated through a set of experiments carried out in lab; also a qualitative evaluation by a heterogeneous group of perspective users, users' relatives, social workers, and experts gave us many positive comments and useful feedbacks for future work.","PeriodicalId":179925,"journal":{"name":"2010 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129311213","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 : 2010-10-25DOI: 10.1109/BIOMS.2010.5610440
Emanuela Marasco, Carlo Sansone
Fingerprint verification systems may be circumvented by fake fingerprints produced using inexpensive materials like gelatin or silicon. An efficient countermeasure against these attacks is given by liveness detection. In the recent literature, different algorithms for detecting signs of vitality have been proposed. The cheapest techniques are software-based and utilize acquired fingerprint images in order to extract static or dynamic characteristics. In this paper, we propose a novel software-based solution for liveness detection based on static features coming out from the visual texture of the image. The reported results show that the use of our features effectively improves the discriminative power (between live and fake fingerprints) achieved by the algorithms proposed during the Liveness Detection Competition 2009.
{"title":"An anti-spoofing technique using multiple textural features in fingerprint scanners","authors":"Emanuela Marasco, Carlo Sansone","doi":"10.1109/BIOMS.2010.5610440","DOIUrl":"https://doi.org/10.1109/BIOMS.2010.5610440","url":null,"abstract":"Fingerprint verification systems may be circumvented by fake fingerprints produced using inexpensive materials like gelatin or silicon. An efficient countermeasure against these attacks is given by liveness detection. In the recent literature, different algorithms for detecting signs of vitality have been proposed. The cheapest techniques are software-based and utilize acquired fingerprint images in order to extract static or dynamic characteristics. In this paper, we propose a novel software-based solution for liveness detection based on static features coming out from the visual texture of the image. The reported results show that the use of our features effectively improves the discriminative power (between live and fake fingerprints) achieved by the algorithms proposed during the Liveness Detection Competition 2009.","PeriodicalId":179925,"journal":{"name":"2010 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128135839","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 : 2010-10-25DOI: 10.1109/BIOMS.2010.5610438
G. Marcialis, P. Mastinu, F. Roli
Serial, or sequential, fusion of multiple biometric matchers has been not thoroughly investigated so far. However, this approach exhibits some advantages with respect to the widely adopted parallel approaches. In this paper, we propose a novel theoretical framework for the assessment of performance of such systems, based on a previous work of the authors. Benefits in terms of performance are theoretically evaluated, as well as estimation errors in the model parameters computation. Model is analyzed from the viewpoint of its pros and cons, by mean of preliminary experiments performed on NIST Biometric Score Set 1.
{"title":"Serial fusion of multi-modal biometric systems","authors":"G. Marcialis, P. Mastinu, F. Roli","doi":"10.1109/BIOMS.2010.5610438","DOIUrl":"https://doi.org/10.1109/BIOMS.2010.5610438","url":null,"abstract":"Serial, or sequential, fusion of multiple biometric matchers has been not thoroughly investigated so far. However, this approach exhibits some advantages with respect to the widely adopted parallel approaches. In this paper, we propose a novel theoretical framework for the assessment of performance of such systems, based on a previous work of the authors. Benefits in terms of performance are theoretically evaluated, as well as estimation errors in the model parameters computation. Model is analyzed from the viewpoint of its pros and cons, by mean of preliminary experiments performed on NIST Biometric Score Set 1.","PeriodicalId":179925,"journal":{"name":"2010 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130725694","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 : 2010-10-25DOI: 10.1109/BIOMS.2010.5610446
G. Pirlo, D. Impedovo
This paper presents a static signature verification system based on a region-oriented strategy. For this purpose, a suitable technique is proposed for the analysis of local stability in static signature and stable regions are selected during the enrollment phase. In the running phase, an unknown specimen is verified through the analysis of the selected regions, on the basis of a well-defined similarity measure. The experimental results, carried out on signatures from the GPDS database, demonstrate the proposed approach.
{"title":"On the measurement of local stability of handwriting: An application to static signature verification","authors":"G. Pirlo, D. Impedovo","doi":"10.1109/BIOMS.2010.5610446","DOIUrl":"https://doi.org/10.1109/BIOMS.2010.5610446","url":null,"abstract":"This paper presents a static signature verification system based on a region-oriented strategy. For this purpose, a suitable technique is proposed for the analysis of local stability in static signature and stable regions are selected during the enrollment phase. In the running phase, an unknown specimen is verified through the analysis of the selected regions, on the basis of a well-defined similarity measure. The experimental results, carried out on signatures from the GPDS database, demonstrate the proposed approach.","PeriodicalId":179925,"journal":{"name":"2010 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114227397","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：