2016 4th International Conference on Biometrics and Forensics (IWBF)最新文献

Considering basic emotional state information in speaker verification 基于基本情绪状态信息的说话人验证

2016 4th International Conference on Biometrics and Forensics (IWBF) Pub Date : 2016-03-03 DOI: 10.1109/IWBF.2016.7449689

P. Staroniewicz

引用次数: 3

BioFoV – an open platform for forensic video analysis and biometric data extraction BioFoV -法医视频分析和生物特征数据提取的开放平台

2016 4th International Conference on Biometrics and Forensics (IWBF) Pub Date : 2016-03-03 DOI: 10.1109/IWBF.2016.7449693

M. Almeida, P. Correia, P. Larsen

引用次数: 3

Age interval and gender prediction using PARAFAC2 applied to speech utterances 基于PARAFAC2的语音年龄间隔和性别预测

2016 4th International Conference on Biometrics and Forensics (IWBF) Pub Date : 2016-03-03 DOI: 10.1109/IWBF.2016.7449694

Evangelia Pantraki, Constantine Kotropoulos, A. Lanitis

{"title":"Age interval and gender prediction using PARAFAC2 applied to speech utterances","authors":"Evangelia Pantraki, Constantine Kotropoulos, A. Lanitis","doi":"10.1109/IWBF.2016.7449694","DOIUrl":"https://doi.org/10.1109/IWBF.2016.7449694","url":null,"abstract":"Important problems in speech soft biometrics include the prediction of speaker's age or gender. Here, the aforementioned problems are addressed in the context of utterances collected during a long time period. A unified framework for age and gender prediction is proposed based on Parallel Factor Analysis 2 (PARAFAC2). PARAFAC2 is applied to a collection of three matrices, namely the speech utterance-feature matrix whose columns are the auditory cortical representations, the speaker age matrix whose columns are indicator vectors of suitable dimension, and the speaker gender matrix whose columns are proper indicator vectors associated to speaker's gender. PARAFAC2 is able to reduce the dimensionality of the auditory cortical representations by projecting these representations onto a semantic space dominated by the age and the gender concepts, yielding a sketch (i.e., a feature vector of reduced dimensions). To predict speaker's age interval associated to a test utterance, the speech utterance sketch is pre-multiplied by the left singular vectors of the speaker age matrix. To predict the gender of the speaker who uttered any test utterance, the speech utterance sketch is pre-multiplied by the left singular vectors of the speaker gender matrix. In both cases, a ranking vector is obtained that is exploited for decision making. Promising results are demonstrated, when the aforementioned framework is applied to the Trinity College Dublin Speaker Ageing Database.","PeriodicalId":282164,"journal":{"name":"2016 4th International Conference on Biometrics and Forensics (IWBF)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133047096","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}

引用次数: 3

Short term re-identification of Automatic Teller Machine (ATM) users via face and body appearance features 通过面部和身体外观特征对自动柜员机(ATM)用户进行短期再识别

2016 4th International Conference on Biometrics and Forensics (IWBF) Pub Date : 2016-03-03 DOI: 10.1109/IWBF.2016.7449682

Guney Kayim, Ekberjan Derman, A. A. Salah

引用次数: 5

First investigation of feasibility of contact-less non-destructive optical sensors to detect, acquire and digitally process forensic handwriting based on pressure information 首次研究了基于压力信息的非接触式无损光学传感器检测、获取和数字化处理法医笔迹的可行性

2016 4th International Conference on Biometrics and Forensics (IWBF) Pub Date : 2016-03-03 DOI: 10.1109/IWBF.2016.7449692

Michael Kalbitz, T. Scheidat, C. Vielhauer

{"title":"First investigation of feasibility of contact-less non-destructive optical sensors to detect, acquire and digitally process forensic handwriting based on pressure information","authors":"Michael Kalbitz, T. Scheidat, C. Vielhauer","doi":"10.1109/IWBF.2016.7449692","DOIUrl":"https://doi.org/10.1109/IWBF.2016.7449692","url":null,"abstract":"Both in biometric and forensic sciences, handwriting modality plays an important role. While in biometrics, the sub-discipline of online analysis utilises recordings of the actual writing process, offline analysis has a close link to handwriting forensics. In the later domain, goals comprise for example writer identification or uncover indented writing of found writing traces on documents. In this paper we study the general feasibility of a new approach to handwriting forensics by means of three contact-less non-destructive 2D/3D optical sensors providing high resolution images in the nanometer range which have already shown great potential for the digitised crime scene forensics e.g for fingerprints or gun cartridges. We perform a three-step concept: First, in a general sensor review we identify one sensor which appears most appropriate for our initial use cases, along with appropriate parametrization. Secondly, we propose a first test setup for the acquisition of handwriting traces on paper. The corresponding data is captured from the first and second layer of a five sheets paper stack. Thirdly, we present and discuss our first results of digital image pre-processing based on topographic information representing the pen pressure during the writing process. Our pre-processing approach is focused on segmenting the writing trace in topographical data. For segmentation of the trace we apply different linear filter like mean or binomial as well as non-linear filter like median.","PeriodicalId":282164,"journal":{"name":"2016 4th International Conference on Biometrics and Forensics (IWBF)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123461456","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}

引用次数: 5

Comparison of PRNU enhancement techniques to generate PRNU fingerprints for biometric source sensor attribution 基于PRNU增强技术生成PRNU指纹的生物特征源传感器归属比较

2016 4th International Conference on Biometrics and Forensics (IWBF) Pub Date : 2016-03-03 DOI: 10.1109/IWBF.2016.7449674

L. Debiasi, A. Uhl

{"title":"Comparison of PRNU enhancement techniques to generate PRNU fingerprints for biometric source sensor attribution","authors":"L. Debiasi, A. Uhl","doi":"10.1109/IWBF.2016.7449674","DOIUrl":"https://doi.org/10.1109/IWBF.2016.7449674","url":null,"abstract":"Identifying the source camera which acquired a given image using the cameras PRNU is a well established task in image forensics, known as camera or device identification. Since digital image sensors are widely used to acquire biometric data, it is eligible that this task can also be performed with biometric sensors and the respective data. This has already been studied in literature. In this paper we focus on a slightly different task, which consists in clustering images acquired with the same sensor in a data set possibly containing images from an unknown number of biometric sensors. Previous work showed unclear results that have been difficult to interpret because of the low quality of the extracted PRNU. In this paper we compare the use of a PRNU enhancement technique to the use of special uncorrelated images acquired with known biometric sensors in this clustering context. We additionally propose extensions of existing source sensor attribution techniques using data from known sensors. Finally, the results of the enhancement approaches and the results using the uncorrelated data acquired with the known sensors are compared and an assessment on whether multiple sensor instances have been used in the different investigated data sets is given.","PeriodicalId":282164,"journal":{"name":"2016 4th International Conference on Biometrics and Forensics (IWBF)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123122860","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}

引用次数: 11

Authorship recognition in a multiparty chat scenario 在多方聊天场景中的作者识别

2016 4th International Conference on Biometrics and Forensics (IWBF) Pub Date : 2016-03-03 DOI: 10.1109/IWBF.2016.7449681

R. Kuzu, Koray Balci, A. A. Salah

引用次数: 2

Empirical validation of likelihood ratio methods – A case study in forensic speaker recognition 似然比方法的实证验证-法医说话人识别的案例研究

2016 4th International Conference on Biometrics and Forensics (IWBF) Pub Date : 2016-03-03 DOI: 10.1109/IWBF.2016.7449678

Filipe Guapo, P. Correia, D. Meuwly, D. V. D. Vloed

引用次数: 3

Speaker specific features and phonemes in speech: a proposal for evaluating a possible interaction 说话者在讲话中的特定特征和音素:评估可能的相互作用的建议

2016 4th International Conference on Biometrics and Forensics (IWBF) Pub Date : 2016-03-03 DOI: 10.1109/IWBF.2016.7449684

N. Yadav, Solange Rossato, Juliette Kahn, J. Bonastre

引用次数: 1

Investigating an objective measure of writer hesitation for forensic analysis of the handwritten signature 为手写体签名的法医学分析研究一种客观的判断笔迹犹豫的方法

2016 4th International Conference on Biometrics and Forensics (IWBF) Pub Date : 2016-03-03 DOI: 10.1109/IWBF.2016.7449686

Tasmina Islam, M. Fairhurst

引用次数: 1