Shaun J. Canavan, Michael P. Kozak, Yong Zhang, J. Sullins, Matthew Shreve, Dmitry Goldgof
{"title":"Face Recognition by Multi-Frame Fusion of Rotating Heads in Videos","authors":"Shaun J. Canavan, Michael P. Kozak, Yong Zhang, J. Sullins, Matthew Shreve, Dmitry Goldgof","doi":"10.1109/BTAS.2007.4401929","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401929","url":null,"abstract":"This paper presents a face recognition study that implicitly utilizes the 3D information in 2D video sequences through multi-sample fusion. The approach is based on the hypothesis that continuous and coherent intensity variations in video frames caused by a rotating head can provide information similar to that of explicit shapes or range images. The fusion was done on the image level to prevent information loss. Experiments were carried out using a data set of over 100 subjects and promising results have been obtained: (1) under regular indoor lighting conditions, rank one recognition rate increased from 91% using a single frame to 100% using 7-frame fusion; (2) under strong shadow conditions, rank one recognition rate increased from 63% using a single frame to 85% using 7-frame fusion.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121444552","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}
{"title":"Comparing Data-driven and Phonetic N-gram Systems for Text-Independent Speaker Verification","authors":"Asmaa El Hannani, D. Petrovska-Delacrétaz","doi":"10.1109/BTAS.2007.4401945","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401945","url":null,"abstract":"Recognition of speaker identity based on modeling the streams produced by phonetic decoders(phonetic speaker recognition) has gained popularity during the past few years. Two of the major problems that arise when phone based systems are being developed are the possible mismatches between the development and evaluation data and the lack of transcribed databases. Data-driven segmentation techniques provide a potential solution to these problems because they do not use transcribed data and can easily be applied on development data minimizing the mismatches. In this paper we compare speaker recognition results using phonetic and data-driven decoders. To this end, we have compared the results obtained with two sets of speaker verification systems; the first one based on data-driven units and the second one on phonetic units. Results obtained on the NIST 2006 Speaker Recognition Evaluation data show that the data-driven approach is comparable to the phonetic one and that further improvements can be achieved by combining both approaches.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123757012","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}
{"title":"Verifying Fingerprint Match by Local Correlation Methods","authors":"Jiang Li, S. Tulyakov, V. Govindaraju","doi":"10.1109/BTAS.2007.4401954","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401954","url":null,"abstract":"Most fingerprint matching algorithms are based on finding correspondences between minutiae in two fingerprints. In this paper we present a modification of minutiae matching method, which utilizes correlation scores between the local neighborhood areas of corresponding minutiae pairs and the edges that connect neighboring matched minutiae pairs. Minutiae based matching approach considers the overall minutiae distribution pattern between the two fingerprints. Neighborhood correlation score represents the local similarity between the matched pair of minutiae. Edge correlation score gives the resemblance of areas that in between the two corresponding minutiae pairs. Thus, both the global minutiae distribution structure and the local matching similarity between the two fingerprints are considered for final decision. The described matching approach has been tested on FVC2002's DB1 and DB3 database. The experimental results confirm the effectiveness of combining matching scores of different origin - minutia matching score and local correlation matching scores.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122673223","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}
{"title":"A Novel Fingerprint Matching Algorithm Based on Minutiae and Global Statistical Features","authors":"Peng Shi, Jie Tian, Qi Su, Xin Yang","doi":"10.1109/BTAS.2007.4401955","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401955","url":null,"abstract":"The performance of automated fingerprint identification system (AFIS) is highly defined by the similarity of effective features in fingerprints. Minutia is one of the most widely used local features in fingerprint matching. In this paper, we introduced two global statistical features of fingerprint image, including the mean ridge width and the normalized quality estimation of the whole image, and proposed a novel fingerprint matching algorithm based on minutiae sets combined with the global statistical features. The algorithm proposed in this paper has the advantage of both local and global features in fingerprint matching. It can improve the accuracy of similarity measure without increasing of time and memory consuming. Experimental results on FVC2004 databases showed that these improvements can make a better matching performance on public domain databases.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132670348","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}
M. Martinez-Diaz, Julian Fierrez, J. Ortega-Garcia
{"title":"Universal Background Models for Dynamic Signature Verification","authors":"M. Martinez-Diaz, Julian Fierrez, J. Ortega-Garcia","doi":"10.1109/BTAS.2007.4401942","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401942","url":null,"abstract":"The applicability of universal background models as a score normalization technique is studied for the case of dynamic signature verification. This technique is commonly used in speaker verification systems. Background models are tested in two different systems based on global features: one based on Parzen windows and another based on adapted Gaussian mixture models. Experiments are carried out in the large MCYT database (16,500 signatures from 330 users) revealing a significant improvement in the overall system performance, specially in the casual impostor scenario.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123700912","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}
F. Alonso-Fernandez, F. Roli, G. Marcialis, Julian Fierrez, J. Ortega-Garcia
{"title":"Comparison of fingerprint quality measures using an optical and a capacitive sensor","authors":"F. Alonso-Fernandez, F. Roli, G. Marcialis, Julian Fierrez, J. Ortega-Garcia","doi":"10.1109/BTAS.2007.4401956","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401956","url":null,"abstract":"Although several image quality measures have been proposed for fingerprints, no work has taken into account the differences among capture devices, and how these differences impact on the image quality. In this paper, several representative measures for assessing the quality fingerprint images are compared using an optical and a capacitive sensor. The capability to discriminate between images of different quality and its relationship with the verification performance is studied. We report differences depending on the sensor, and interesting relationships between sensor technology and features used for quality assessment are also pointed out.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121254728","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}
{"title":"Improving Biometric Device Interoperability by Likelihood Ratio-based Quality Dependent Score Normalization","authors":"N. Poh, Josef Kittler, T. Bourlai","doi":"10.1109/BTAS.2007.4401964","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401964","url":null,"abstract":"As biometric technology is being deployed, it will be a common situation to have a template acquired by one biometric device to be used by another during testing. In our problem formulation, we assume that the device may not be known to the system but can be inferred by a set of automatically derived quality measures. The proposed method of device inference results in a novel device-specific quality-dependent score normalisation called the DS-norm. Experiments based on the BioSecure DS2 data set confirm the benefits and feasibility of the proposed approach.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130847928","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}
{"title":"Hidden Markov Models for Spoken Signature Verification","authors":"A. Humm, J. Hennebert, R. Ingold","doi":"10.1109/BTAS.2007.4401960","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401960","url":null,"abstract":"In this paper we report on the developments of an efficient user authentication system using combined acquisition of online signature and speech modalities. In our project, these two modalities are simultaneously recorded by asking the user to utter what she/he is writing. The main benefit of this multimodal approach is a better accuracy at no extra costs in terms of access time or inconvenience. More specifically, we report in this paper on significant improvements of our initial system that was based on Gaussian Mixture Models (GMMs) applied independently to the pen and voice signal. We show that the GMMs can be advantageously replaced by Hidden Markov Models (HMMs) provided that the number of state used for the topology is optimized and provided that the model parameters are trained with a Maximum a Posteriori (MAP) adaptation procedure instead of the classically used Expectation Maximization (EM). The evaluations are conducted on spoken signatures taken from the MylDea multimodal database. Consistently with our previous evaluation of the GMM system, we observe for the HMM system that the use of both speech and handwriting modalities outperforms significantly these modalities used alone. We also report on the evaluations of different score fusion strategies.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123445948","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}
{"title":"Proposed FPGA Hardware Architecture for High Frame Rate (≫100 fps) Face Detection Using Feature Cascade Classifiers","authors":"Hung-Chih Lai, M. Savvides, Tsuhan Chen","doi":"10.1109/BTAS.2007.4401930","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401930","url":null,"abstract":"Face detection is the first and most crucial step in any face recognition systems with applications to face tracking, recognition and automatic surveillance. AdaBoost based face detection training methods have been proposed for producing a rapidly fast detection implementation compared to other methods using the integral image for evaluating a series of weak classifiers very fast. Current software version implementations can achieve about 15-25 frames per second (fps) with a tunable compromise between detection accuracy and speed. In this paper, a novel hardware architecture design on FPGA based on AdaBoost face training and detection algorithm for detecting faces in high resolution images at high frame rates (>100 fps) is proposed. The proposed architecture can evaluate each sub-window in a single clock cycle, which is the fastest possible speed land is limited by the H/W clock running speed. Thus in this proposed approach, detection speed is independent from the number of weak classifiers implemented. The proposed architecture is verified on Xilinx Virtex-II Pro FPGA platform where experimental results show that the speed and memory outperform previous approaches in literature, achieving 143 fps for image size of 640 by 480 pixels using a single scan window. Parallelizing the scan window can lead to double/triple this speed and is dependent on the gate capacity of the FPGA.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129242073","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}
{"title":"Understanding Cognitive and Affective States Using Eyelid Movements","authors":"R. Heishman, Zoran Duric, H. Wechsler","doi":"10.1109/BTAS.2007.4401944","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401944","url":null,"abstract":"Biometrics related to the eye region are of particular interest in a range of applications -from identification to adaptive interfaces. This paper describes a technique for monitoring dynamic eye region biometrics (i.e., blinking) as unique indicators of cognitive and affective states in subjects involved in HCI scenarios. We integrate a novel collection of robust, minimally-intrusive computer vision techniques for effective interpretation of eye blink behaviors using color video, including k-means clustering for learning, histograms and normal flow fields for steady-state and transitional tracking, and a deterministic finite state machine for state analysis. Sample results that illustrate the application of our approach are presented.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116365178","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}