Pub Date : 2007-09-01DOI: 10.1109/BCC.2007.4430549
Yongjin Wang, K. Plataniotis
This paper presents a method for changeable cryptographic key generation using face biometrics signal. A previously introduced scheme, fuzzy vault, is utilized for secure binding of randomly generated key with extracted biometrics features. The major technical difficulty is to map noisy biometrics representation to the exactly correct key. In this paper, the proposed method is based on 2-dimensional quantization of distance vectors between biometrics features and pairs of random vectors. A windowing process is applied to tolerate the variations of biometrics signals. Further, we also introduce a two-factor scheme, where the quantized distance vectors are generated with user-dependent random vectors. By integrating a second factor, both the biometrics and the key are changeable, and zero error rate can be obtained.
{"title":"Fuzzy Vault for Face Based Cryptographic Key Generation","authors":"Yongjin Wang, K. Plataniotis","doi":"10.1109/BCC.2007.4430549","DOIUrl":"https://doi.org/10.1109/BCC.2007.4430549","url":null,"abstract":"This paper presents a method for changeable cryptographic key generation using face biometrics signal. A previously introduced scheme, fuzzy vault, is utilized for secure binding of randomly generated key with extracted biometrics features. The major technical difficulty is to map noisy biometrics representation to the exactly correct key. In this paper, the proposed method is based on 2-dimensional quantization of distance vectors between biometrics features and pairs of random vectors. A windowing process is applied to tolerate the variations of biometrics signals. Further, we also introduce a two-factor scheme, where the quantized distance vectors are generated with user-dependent random vectors. By integrating a second factor, both the biometrics and the key are changeable, and zero error rate can be obtained.","PeriodicalId":389417,"journal":{"name":"2007 Biometrics Symposium","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130745718","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 : 2007-09-01DOI: 10.1109/BCC.2007.4430555
G. K. Singhal, Pavan Ramkumar
In this paper, we explore visually evoked potentials (VEPs) as a potential tool for biometric identification. Using a clinical stimulation paradigm, single channel pattern onset VEPs are recorded from raw EEG from 10 healthy male subjects aged between 20 and 24. Following this, two feature extraction techniques are employed to characterize the signals. Specifically, a novel, physiologically relevant peak matching algorithm is proposed and its performance is compared to features obtained from multi-resolution wavelet analysis. Once suitably characterized, the VEPs from different individuals are classified using a standard distance-measure based algorithm.
{"title":"Person Identification Using Evoked Potentials and Peak Matching","authors":"G. K. Singhal, Pavan Ramkumar","doi":"10.1109/BCC.2007.4430555","DOIUrl":"https://doi.org/10.1109/BCC.2007.4430555","url":null,"abstract":"In this paper, we explore visually evoked potentials (VEPs) as a potential tool for biometric identification. Using a clinical stimulation paradigm, single channel pattern onset VEPs are recorded from raw EEG from 10 healthy male subjects aged between 20 and 24. Following this, two feature extraction techniques are employed to characterize the signals. Specifically, a novel, physiologically relevant peak matching algorithm is proposed and its performance is compared to features obtained from multi-resolution wavelet analysis. Once suitably characterized, the VEPs from different individuals are classified using a standard distance-measure based algorithm.","PeriodicalId":389417,"journal":{"name":"2007 Biometrics Symposium","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131971093","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 : 2007-09-01DOI: 10.1109/BCC.2007.4430538
Yi Chen, A.K. Jain
There are fundamental differences in the way fingerprints are compared by forensic examiners and current automatic systems. For example, while automatic systems focus mainly on the quantitative measures of fingerprint minutiae (ridge ending and bifurcation points), forensic examiners often analyze details of intrinsic ridge characteristics and relational information. This process, known as qualitative friction ridge analysis [1], includes examination of ridge shape, pores, dots, incipient ridges, etc. This explains the challenges that current automatic systems face in processing partial fingerprints, mostly seen in latents. The forensics and automatic fingerprint identification systems (AFIS) communities have been active in standardizing the definition of extended feature set, as well as quantifying the relevance and reliability of these features for automatic matching systems. CDEFFS (committee to define an extended feature set) has proposed a working draft on possible definitions and representations of extended features [2]. However, benefits of utilizing these extended features in automatic systems are not yet known. While fingerprint matching technology is quite mature for matching tenprints [3], matching partial fingerprints, especially latents, still needs a lot of improvement. We propose an algorithm to extract two major level 3 feature types, dots and incipients, based on local phase symmetry and demonstrate their effectiveness in partial print matching. Since dots and incipients can be easily encoded by forensic examiners, we believe the results of this research will have benefits to next generation identification (NGI) systems.
{"title":"Dots and Incipients: Extended Features for Partial Fingerprint Matching","authors":"Yi Chen, A.K. Jain","doi":"10.1109/BCC.2007.4430538","DOIUrl":"https://doi.org/10.1109/BCC.2007.4430538","url":null,"abstract":"There are fundamental differences in the way fingerprints are compared by forensic examiners and current automatic systems. For example, while automatic systems focus mainly on the quantitative measures of fingerprint minutiae (ridge ending and bifurcation points), forensic examiners often analyze details of intrinsic ridge characteristics and relational information. This process, known as qualitative friction ridge analysis [1], includes examination of ridge shape, pores, dots, incipient ridges, etc. This explains the challenges that current automatic systems face in processing partial fingerprints, mostly seen in latents. The forensics and automatic fingerprint identification systems (AFIS) communities have been active in standardizing the definition of extended feature set, as well as quantifying the relevance and reliability of these features for automatic matching systems. CDEFFS (committee to define an extended feature set) has proposed a working draft on possible definitions and representations of extended features [2]. However, benefits of utilizing these extended features in automatic systems are not yet known. While fingerprint matching technology is quite mature for matching tenprints [3], matching partial fingerprints, especially latents, still needs a lot of improvement. We propose an algorithm to extract two major level 3 feature types, dots and incipients, based on local phase symmetry and demonstrate their effectiveness in partial print matching. Since dots and incipients can be easily encoded by forensic examiners, we believe the results of this research will have benefits to next generation identification (NGI) systems.","PeriodicalId":389417,"journal":{"name":"2007 Biometrics Symposium","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134188142","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 : 2007-09-01DOI: 10.1109/BCC.2007.4430539
M. Rahmes, J. Allen, A. Elharti, G. Tenali
Manual latent fingerprint reconstruction to restore missing ridges is a tedious, time consuming, and expensive process. Latent fingerprint ridges are typically partially smudged, partially missing, aged, etc. This type of fingerprint cannot be used in the court of law directly to garner a conviction unless it can be matched to a known fingerprint. However, latent prints minimize the search for potential suspects and finding missing people. We propose an automated reconstruction method which minimizes manual restoration. Our nonlinear partial differential equation (PDE) and exemplar inpainting processes can aid the fingerprint expert. Larger missing regions are repaired using our coherent-based exemplar inpainting algorithm. PDE inpainting is used to fill small fissures in ridge structure. Ridge-lines are sharpened with anisotropic diffusion filters. These technologies improve latent fingerprint computer matching by allowing more minutiae. Accuracy assessment for inpainting missing ridges is described.
{"title":"Fingerprint Reconstruction Method Using Partial Differential Equation and Exemplar-Based Inpainting Methods","authors":"M. Rahmes, J. Allen, A. Elharti, G. Tenali","doi":"10.1109/BCC.2007.4430539","DOIUrl":"https://doi.org/10.1109/BCC.2007.4430539","url":null,"abstract":"Manual latent fingerprint reconstruction to restore missing ridges is a tedious, time consuming, and expensive process. Latent fingerprint ridges are typically partially smudged, partially missing, aged, etc. This type of fingerprint cannot be used in the court of law directly to garner a conviction unless it can be matched to a known fingerprint. However, latent prints minimize the search for potential suspects and finding missing people. We propose an automated reconstruction method which minimizes manual restoration. Our nonlinear partial differential equation (PDE) and exemplar inpainting processes can aid the fingerprint expert. Larger missing regions are repaired using our coherent-based exemplar inpainting algorithm. PDE inpainting is used to fill small fissures in ridge structure. Ridge-lines are sharpened with anisotropic diffusion filters. These technologies improve latent fingerprint computer matching by allowing more minutiae. Accuracy assessment for inpainting missing ridges is described.","PeriodicalId":389417,"journal":{"name":"2007 Biometrics Symposium","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134402301","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 : 2007-09-01DOI: 10.1109/BCC.2007.4430534
W. Scheirer, T. Boult
This paper is a security analysis of leading privacy enhanced technologies (PETs) for biometrics including biometric fuzzy vaults (BFV) and biometric encryption (BE). The lack of published attacks, combined with various "proven" security properties has been taken by some as a sign that these technologies are ready for deployment. While some of the existing BFV and BE techniques do have "proven" security properties, those proofs make assumptions that may not, in general, be valid for biometric systems. We briefly review some of the other known attacks against BFV and BE techniques. We introduce three disturbing classes of attacks against PET techniques including attack via record multiplicity, surreptitious key-inversion attack, and novel blended substitution attacks. The paper ends with a discussion of the requirements for an architecture to address the privacy and security requirements.
{"title":"Cracking Fuzzy Vaults and Biometric Encryption","authors":"W. Scheirer, T. Boult","doi":"10.1109/BCC.2007.4430534","DOIUrl":"https://doi.org/10.1109/BCC.2007.4430534","url":null,"abstract":"This paper is a security analysis of leading privacy enhanced technologies (PETs) for biometrics including biometric fuzzy vaults (BFV) and biometric encryption (BE). The lack of published attacks, combined with various \"proven\" security properties has been taken by some as a sign that these technologies are ready for deployment. While some of the existing BFV and BE techniques do have \"proven\" security properties, those proofs make assumptions that may not, in general, be valid for biometric systems. We briefly review some of the other known attacks against BFV and BE techniques. We introduce three disturbing classes of attacks against PET techniques including attack via record multiplicity, surreptitious key-inversion attack, and novel blended substitution attacks. The paper ends with a discussion of the requirements for an architecture to address the privacy and security requirements.","PeriodicalId":389417,"journal":{"name":"2007 Biometrics Symposium","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127168467","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 : 2007-09-01DOI: 10.1109/BCC.2007.4430552
Hugo Gamboa, Ana L. N. Fred, Anil K. Jain
We introduce a biometric trait based on the user behavior extracted from his interaction with a Web page. We propose the integration of this soft biometric trait in a conventional login Internet page to enhance the security of the system. We call this security layer WebBiometrics. This layer monitors the user mouse movements while he clicks his PIN code numbers. The proposed biometric method provides a non-intrusive soft behavioral biometric add-on to enhance on-line security. We describe the functionality of the system, the set of algorithms developed for the verification framework and preliminary experimental results. We also present quantitative measures of security enhancement offered by the introduction of this soft biometric compared to a PIN only based Web access.
{"title":"Webbiometrics: User Verification Via Web Interaction","authors":"Hugo Gamboa, Ana L. N. Fred, Anil K. Jain","doi":"10.1109/BCC.2007.4430552","DOIUrl":"https://doi.org/10.1109/BCC.2007.4430552","url":null,"abstract":"We introduce a biometric trait based on the user behavior extracted from his interaction with a Web page. We propose the integration of this soft biometric trait in a conventional login Internet page to enhance the security of the system. We call this security layer WebBiometrics. This layer monitors the user mouse movements while he clicks his PIN code numbers. The proposed biometric method provides a non-intrusive soft behavioral biometric add-on to enhance on-line security. We describe the functionality of the system, the set of algorithms developed for the verification framework and preliminary experimental results. We also present quantitative measures of security enhancement offered by the introduction of this soft biometric compared to a PIN only based Web access.","PeriodicalId":389417,"journal":{"name":"2007 Biometrics Symposium","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125475188","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 : 2007-09-01DOI: 10.1109/bcc.2007.4430532
Robert K. Rowe, U. Uludag, Meltem Demirkus, Sujan T. V. Parthasaradhi, Anil K. Jain
We describe the design and development of a prototype whole-hand imaging system. The sensor is based on multispectral technology that is able to provide hand shape, fingerprints and palmprint modalities of a user's hand by a single user interaction with the sensor. A clear advantage of our system over other unimodal sensors for these modalities include: (i) faster acquisition time, (ii) better quality images, and (iii) ability to provide spoof detection. Initial results on a medium-size database show good recognition performance based on individual modalities as well as after fusing multiple fingers and fusing finger and palm. The prototype is being refined in order to improve performance even further.
{"title":"A Multispectral Whole-Hand Biometric Authentication System","authors":"Robert K. Rowe, U. Uludag, Meltem Demirkus, Sujan T. V. Parthasaradhi, Anil K. Jain","doi":"10.1109/bcc.2007.4430532","DOIUrl":"https://doi.org/10.1109/bcc.2007.4430532","url":null,"abstract":"We describe the design and development of a prototype whole-hand imaging system. The sensor is based on multispectral technology that is able to provide hand shape, fingerprints and palmprint modalities of a user's hand by a single user interaction with the sensor. A clear advantage of our system over other unimodal sensors for these modalities include: (i) faster acquisition time, (ii) better quality images, and (iii) ability to provide spoof detection. Initial results on a medium-size database show good recognition performance based on individual modalities as well as after fusing multiple fingers and fusing finger and palm. The prototype is being refined in order to improve performance even further.","PeriodicalId":389417,"journal":{"name":"2007 Biometrics Symposium","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130281656","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 : 2007-09-01DOI: 10.1109/BCC.2007.4430547
J. Doublet, O. Lepetit, M. Revenu
More and more research have been developed very recently for automatic hand recognition. This paper proposes a new method for contactless hand authentication in complex images with low cost devices. Our system uses skin color and hand shape information for hand detection process. Next, the palm is extracted and characterized by a bank of Gabor filters. Finally, the palm features are compared with a distribution estimation given an optimal discrimination. The experimental results present an error rate lower than 1.7% with a population of 49 people.
{"title":"Contactless Hand Recognition Based on Distribution Estimation","authors":"J. Doublet, O. Lepetit, M. Revenu","doi":"10.1109/BCC.2007.4430547","DOIUrl":"https://doi.org/10.1109/BCC.2007.4430547","url":null,"abstract":"More and more research have been developed very recently for automatic hand recognition. This paper proposes a new method for contactless hand authentication in complex images with low cost devices. Our system uses skin color and hand shape information for hand detection process. Next, the palm is extracted and characterized by a bank of Gabor filters. Finally, the palm features are compared with a distribution estimation given an optimal discrimination. The experimental results present an error rate lower than 1.7% with a population of 49 people.","PeriodicalId":389417,"journal":{"name":"2007 Biometrics Symposium","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131502599","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 : 2007-09-01DOI: 10.1109/BCC.2007.4430529
Scott Von Duhn, M. Ko, L. Yin, Terry Hung, Xiaozhou Wei
3D face recognition has been researched intensively in recent decades. Most 3D data (so called range facial data) are obtained from 3D range imaging systems. Such data representations have been proven effective for face recognition in 3D space. However, obtaining such data requires subject cooperation in a constrained environment, which is not practical for many real applications of video surveillance. It is therefore in high demand to use regular video cameras to generate 3D face models for further classification. The goal of our research is to develop a method of tracking feature points on a face in multiple views in order to build 3D models of individual faces. We proposed a three-view based video tracking and model creation algorithm, which is based on the active appearance model and a generic facial model. We will describe how to build useful individual models over time, and validate the created dynamic model sequences. Our experiments demonstrate the feasibility of the proposed work through the application for face recognition.
{"title":"Three-View Surveillance Video Based Face Modeling for Recogniton","authors":"Scott Von Duhn, M. Ko, L. Yin, Terry Hung, Xiaozhou Wei","doi":"10.1109/BCC.2007.4430529","DOIUrl":"https://doi.org/10.1109/BCC.2007.4430529","url":null,"abstract":"3D face recognition has been researched intensively in recent decades. Most 3D data (so called range facial data) are obtained from 3D range imaging systems. Such data representations have been proven effective for face recognition in 3D space. However, obtaining such data requires subject cooperation in a constrained environment, which is not practical for many real applications of video surveillance. It is therefore in high demand to use regular video cameras to generate 3D face models for further classification. The goal of our research is to develop a method of tracking feature points on a face in multiple views in order to build 3D models of individual faces. We proposed a three-view based video tracking and model creation algorithm, which is based on the active appearance model and a generic facial model. We will describe how to build useful individual models over time, and validate the created dynamic model sequences. Our experiments demonstrate the feasibility of the proposed work through the application for face recognition.","PeriodicalId":389417,"journal":{"name":"2007 Biometrics Symposium","volume":"374 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122348858","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 : 2007-09-01DOI: 10.1109/BCC.2007.4430548
F. Alonso-Fernandez, M. Fairhurst, Julian Fierrez, J. Ortega-Garcia
The performance of two popular approaches for off-line signature verification in terms of signature legibility and signature type is studied. We investigate experimentally if the knowledge of letters, syllables or name instances can help in the process of imitating a signature. Experimental results are given on a sub-corpus of the MCYT signature database for random and skilled forgeries. We use for our experiments two machine experts, one based on global image analysis and statistical distance measures, and the second based on local image analysis and Hidden Markov Models. Verification results are reported in terms of Equal Error Rate (EER), False Acceptance Rate (FAR) and False Rejection Rate (FRR).
{"title":"Impact of Signature Legibility and Signature Type in Off-Line Signature Verification","authors":"F. Alonso-Fernandez, M. Fairhurst, Julian Fierrez, J. Ortega-Garcia","doi":"10.1109/BCC.2007.4430548","DOIUrl":"https://doi.org/10.1109/BCC.2007.4430548","url":null,"abstract":"The performance of two popular approaches for off-line signature verification in terms of signature legibility and signature type is studied. We investigate experimentally if the knowledge of letters, syllables or name instances can help in the process of imitating a signature. Experimental results are given on a sub-corpus of the MCYT signature database for random and skilled forgeries. We use for our experiments two machine experts, one based on global image analysis and statistical distance measures, and the second based on local image analysis and Hidden Markov Models. Verification results are reported in terms of Equal Error Rate (EER), False Acceptance Rate (FAR) and False Rejection Rate (FRR).","PeriodicalId":389417,"journal":{"name":"2007 Biometrics Symposium","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130987960","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：