{"title":"Effects of Time Normalization on the Accuracy of Dynamic Time Warping","authors":"Olaf Henniger, Sascha Müller","doi":"10.1109/BTAS.2007.4401946","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401946","url":null,"abstract":"This paper revisits dynamic time warping, a method for assessing the dissimilarity of time series. In particular, this paper provides theoretical and experimental evidence showing that uncritical normalizing the length of the time series to be compared has a detrimental effect on the recognition accuracy in application domains such as on-line signature recognition, where the length of compared time series matters for their classification as match or non-match.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"147 suppl_2 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":"126849001","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":"Quantitative Analysis of 3D Face Reconstruction using Annealing based Approach","authors":"S. Amin, D. Gillies","doi":"10.1109/BTAS.2007.4401926","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401926","url":null,"abstract":"3D shape reconstruction from 2D images is an inverse problem, and is therefore mathematically ill-posed. In most of the previous research no quantitative measures of quality of 3D reconstruction have been used. Instead visual and indirect measures such as recognition results are used as the measure of quality of 3D reconstruction. This paper presents an analysis by synthesis method for solving 3D face reconstruction problems using anatomical landmarks and intensity from 2D frontal face images. For evaluating the quality of 3D shape reconstruction two objective measures 3D shape error and 2D shape error are proposed. In order to improve the quality of 3D shape reconstruction a number of steps are proposed. Firstly, the 3D shape model is constructed by establishing a dense correspondence using rigid and non rigid surface registration. Secondly shape estimation is made robust by incorporating simulated annealing into the multidimensional amoeba optimization used for recovering shape parameters.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"8 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":"116160055","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":"Multispectral Local Binary Pattern Histogram for Component-based Color Face Verification","authors":"Chi-Ho Chan, J. Kittler, K. Messer","doi":"10.1109/BTAS.2007.4401951","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401951","url":null,"abstract":"A novel discriminative face representation derived by the Linear Discriminant Analysis (LDA) of multispectral Local binary pattern histograms is proposed for color face recognition. The color face image is first photometrically normalized and partitioned into several non-overlapping regions. In each region, multispectral local binary pattern histograms are extracted and concatenated into a regional feature. The feature is then projected into a LDA space to be used as a regional discriminative facial descriptor. The overall similarity score is obtained by fusing the similarity scores of the regional descriptors. The method is implemented and tested in face verification on the XM2VTS and FRGC 2.0 databases with very promising results.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"10 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":"122747641","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":"Towards Real-World Face De-Identification","authors":"R. Gross, L. Sweeney","doi":"10.1109/BTAS.2007.4401915","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401915","url":null,"abstract":"A wide range of technological advances have helped to make extensive image and video acquisition close to effortless. As a consequence many applications which capture image data of people for either immediate inspection or storage and subsequent sharing have become possible. Along with these improved recording capabilities, however, come concerns about the privacy of people visible in the scene. While algorithms have been proposed to de-identify images, currently available methods are still lacking. In this paper we propose a general framework for the de-identification of images which subsumes a number of previously introduced approaches. Unlike the ad-hoc methods currently used in the field our algorithms aim at providing privacy guarantees. In experiments on illumination-and expression-variant face datasets we show that the proposed algorithms achieve the desired privacy protection while minimally distorting the data.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"15 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":"129890192","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 Model-Based Signature Verification System","authors":"A. Zimmer, L. Ling","doi":"10.1109/BTAS.2007.4401943","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401943","url":null,"abstract":"In this work a hybrid handwritten signature verification system architecture is built where the segmentation of the signature is done inspired by a vectorial delta-lognormal kinematic handwritten reproduction model. The acquisition module processes dynamic data sampled from a digitizer tablet creating a prototype signature that is saved in a database with the correspondent feature's thresholds. The verification is done over the image of the test signature without the presence of the author. Details about the segmentation methodology are presented along with the system's architecture and performance results.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"279 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":"134435492","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":"Using a Multi-Instance Enrollment Representation to Improve 3D Face Recognition","authors":"T. Faltemier, K. Bowyer, P. Flynn","doi":"10.1109/BTAS.2007.4401928","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401928","url":null,"abstract":"One of most challenging problems in 3D face recognition is matching images containing different expressions in the probe and gallery sets. Face images containing the same expression can be accurately identified; however, realistic biometric scenarios are not guaranteed to have the same expression in both probe and gallery. In this paper we examine a multi-instance enrollment representation as a means to improve the performance of a 3D face recognition system. Experiments are conducted on the ND-2006 data corpus which is the largest set of 3D face scans available to the research community. In addition, we show that using a gallery comprised of multiple expressions offers consistently higher performance than using any single expression.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"14 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":"131312959","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":"Ear Recognition based on 2D Images","authors":"Li Yuan, Zhichun Mu","doi":"10.1109/BTAS.2007.4401941","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401941","url":null,"abstract":"Research of ear recognition and its application is a new subject in the field of biometrics authentication. Ear normalization and alignment is a fundamental module in the ear recognition system. Traditional manually normalization method is not suitable for an automatic recognition system. In this paper, an automatic ear normalization method is proposed based on improved Active Shape Model (ASM). This algorithm is applied on the USTB ear database for ear normalization. Then Full-space Linear Discriminant Analysis (FSLDA) is applied for ear recognition on the normalized ear images with different rotation variations. Experiments are performed on USTB ear image database. Recognition rates show that based on the right ear images, the acceptable head rotation range for ear recognition is between the right rotation of 20 degree to the left rotation of 10 degree.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"14 1 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":"115714800","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 fingerprint matching algorithm based on alignment using LPD and GCD minutia descriptors","authors":"G. Chao, Shyh-Kang Jeng, Shung-Shing Lee","doi":"10.1109/BTAS.2007.4401957","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401957","url":null,"abstract":"Although various algorithms have been proposed, accurate fingerprint matching remains an unresolved problem. This paper describes a minutiae based fingerprint matching algorithm that uses minutia descriptors to help finding the optimal global transformation between two different fingerprints quickly. Two different minutia descriptors, the local patch descriptor (LPD) and the geometrical configuration descriptor (GCD), are used in this paper. A small set of matched pairs between two different fingerprints are found first based on these minutia descriptors. A rough global transformation will be found in these small set of matched pairs by RANSAC algorithm, then a proposed method of verifying the matching result is applied to filter matched pairs that extracted from RANSAC algorithm. The final global transformation will be overdetermined by the filtered matched pairs. The matching result will be calculated by the final global transformation. Experimental results show that the occurrence of misalignment is dramatically reduced and that matching accuracy is improved at the same time.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"356 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":"115935978","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":"Robust Part-Based Face Recognition Using Boosting and Transduction","authors":"Fayin Li, H. Wechsler","doi":"10.1109/BTAS.2007.4401923","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401923","url":null,"abstract":"The challenge for biometrics is to withstand image variability and defend against impostors seeking to breach security. The impostors attempt to hide and/or alter the information needed for their identification. While faces can be partially occluded and/or disguised some of their parts remain unchanged and can still be properly detected and authenticated. Towards that end this paper advocates robust part-based face recognition using boosting and transduction. The face representation used spans a multi-resolution (golden ratio) grid that captures partial information at different scales in order to accommodate different surveillance scenarios including human identification from distance. The face components are defined across the eyes, nose, mouth, eye and nose, nose and mouth, and the like, and encode both facial parts and their second order relationships. The parts, clusters of local patches described using similar SIFT features, are modeled using an exemplar based representation. The model free and non-parametric weak learners found by transduction, which correspond to parts and their relationships, compete to build up a strong boosting classifier. The feasibility of the novel approach, using FRGC (UND) database, shows robustness to uncontrolled lighting condition, different facial expressions, and occlusion.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"29 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":"124163526","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}
J. Beveridge, A. Alvarez, J. Saraf, W. Fisher, P. Flynn, J. Gentile
{"title":"Face Detection Algorithm and Feature Performance on FRGC 2.0 Imagery","authors":"J. Beveridge, A. Alvarez, J. Saraf, W. Fisher, P. Flynn, J. Gentile","doi":"10.1109/BTAS.2007.4401950","DOIUrl":"https://doi.org/10.1109/BTAS.2007.4401950","url":null,"abstract":"The performance of three well known face detection algorithms and four alternative types of features are characterized using face data from the Face Recognition Grand Challenge. The three algorithms are a semi-naive Bayesian classifier, a neural network called a SNoW, and a cascade classifier using Haar wavelets. For the first two algorithms, ROC analysis is used to assess the relative value of wavelet features compared to simpler pixel features. No universally best feature is observed, and for imagery acquired under uncontrolled lighting, pixels perform slightly better than wavelets. The cascade classifier is found to be impossible to train in the same fashion as the other algorithms, but it is also found to perform very well using a training configuration supplied along with the algorithm as part of the OpenCV library.","PeriodicalId":257967,"journal":{"name":"2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems","volume":"26 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":"115105286","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}