Pub Date : 2022-02-04DOI: 10.5772/intechopen.101990
Masashi Nishiyama
We determine and use the gaze distribution of observers viewing images of subjects for gender recognition. In general, people look at informative regions when determining the gender of subjects in images. Based on this observation, we hypothesize that the regions corresponding to the concentration of the observer gaze distributions contain discriminative features for gender recognition. We generate the gaze distribution from observers while they perform the task of manually recognizing gender from subject images. Next, our gaze-guided feature extraction assigns high weights to the regions corresponding to clusters in the gaze distribution, thereby selecting discriminative features. Experimental results show that the observers mainly focused on the head region, not the entire body. Furthermore, we demonstrate that the gaze-guided feature extraction significantly improves the accuracy of gender recognition.
{"title":"Feature Extraction Using Observer Gaze Distributions for Gender Recognition","authors":"Masashi Nishiyama","doi":"10.5772/intechopen.101990","DOIUrl":"https://doi.org/10.5772/intechopen.101990","url":null,"abstract":"We determine and use the gaze distribution of observers viewing images of subjects for gender recognition. In general, people look at informative regions when determining the gender of subjects in images. Based on this observation, we hypothesize that the regions corresponding to the concentration of the observer gaze distributions contain discriminative features for gender recognition. We generate the gaze distribution from observers while they perform the task of manually recognizing gender from subject images. Next, our gaze-guided feature extraction assigns high weights to the regions corresponding to clusters in the gaze distribution, thereby selecting discriminative features. Experimental results show that the observers mainly focused on the head region, not the entire body. Furthermore, we demonstrate that the gaze-guided feature extraction significantly improves the accuracy of gender recognition.","PeriodicalId":180604,"journal":{"name":"Recent Advances in Biometrics [Working Title]","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132318039","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 : 2022-02-03DOI: 10.5772/intechopen.101975
E. Fedorov, T. Utkina, Tetyana Neskorodeva
The preliminary stage of the personality biometric identification on a voice is voice signal filtering. For biometric identification are considered and in number investigated the following methods of noise suppression in a voice signal. The smoothing adaptive linear time filtering (algorithm of the minimum root mean square error, an algorithm of recursive least squares, an algorithm of Kalman filtering, a Lee algorithm), the smoothing adaptive linear frequency filtering (the generalized method, the MLEE (maximum likelihood envelope estimation) method, a wavelet analysis with threshold processing (universal threshold, SURE (Stein’s Unbiased Risk Estimator)-threshold, minimax threshold, FDR (False Discovery Rate)-threshold, Bayesian threshold were used), the smoothing non-adaptive linear time filtering (the arithmetic mean filter, the normalized Gauss’s filter, the normalized binomial filter), the smoothing nonlinear filtering (geometric mean filter, the harmonic mean filter, the contraharmonic filter, the α-trimmed mean filter, the median filter, the rank filter, the midpoint filter, the conservative filter, the morphological filter). Results of a numerical research of denoising methods for voice signals people from the TIMIT (Texas Instruments and Massachusetts Institute of Technology) database which were noise an additive Gaussian noise and multiplicative Gaussian noise were received.
{"title":"A Voice Signal Filtering Methods for Speaker Biometric Identification","authors":"E. Fedorov, T. Utkina, Tetyana Neskorodeva","doi":"10.5772/intechopen.101975","DOIUrl":"https://doi.org/10.5772/intechopen.101975","url":null,"abstract":"The preliminary stage of the personality biometric identification on a voice is voice signal filtering. For biometric identification are considered and in number investigated the following methods of noise suppression in a voice signal. The smoothing adaptive linear time filtering (algorithm of the minimum root mean square error, an algorithm of recursive least squares, an algorithm of Kalman filtering, a Lee algorithm), the smoothing adaptive linear frequency filtering (the generalized method, the MLEE (maximum likelihood envelope estimation) method, a wavelet analysis with threshold processing (universal threshold, SURE (Stein’s Unbiased Risk Estimator)-threshold, minimax threshold, FDR (False Discovery Rate)-threshold, Bayesian threshold were used), the smoothing non-adaptive linear time filtering (the arithmetic mean filter, the normalized Gauss’s filter, the normalized binomial filter), the smoothing nonlinear filtering (geometric mean filter, the harmonic mean filter, the contraharmonic filter, the α-trimmed mean filter, the median filter, the rank filter, the midpoint filter, the conservative filter, the morphological filter). Results of a numerical research of denoising methods for voice signals people from the TIMIT (Texas Instruments and Massachusetts Institute of Technology) database which were noise an additive Gaussian noise and multiplicative Gaussian noise were received.","PeriodicalId":180604,"journal":{"name":"Recent Advances in Biometrics [Working Title]","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131306481","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 : 2022-01-15DOI: 10.5772/intechopen.101686
David Palma, Pier Luca Montessoro
With the proliferation of automated systems for reliable and highly secure human authentication and identification, the importance of technological solutions in biometrics is growing along with security awareness. Indeed, conventional authentication methodologies, consisting of knowledge-based systems that make use of something you know (e.g., username and password) and token-based systems that make use of something you have (e.g., identification card), are not able to meet the strict requirements of reliable security applications. Conversely, biometric systems make use of behavioral (extrinsic) and/or physiological (intrinsic) human characteristics, overcoming the security issues affecting the conventional methods for personal authentication. This book chapter provides an overview of the most commonly used biometric traits along with their properties, the various biometric system operating modalities as well as various security aspects related to these systems. In particular, it will be discussed the different stages involved in a biometric recognition process and further discuss various threats that can be exploited to compromise the security of a biometric system. Finally, in order to evaluate the systems’ performance, metrics must be adopted. The most widely used metrics are, therefore, discussed in relation to the provided system accuracy and security, and applicability in real-world deployments.
{"title":"Biometric-Based Human Recognition Systems: An Overview","authors":"David Palma, Pier Luca Montessoro","doi":"10.5772/intechopen.101686","DOIUrl":"https://doi.org/10.5772/intechopen.101686","url":null,"abstract":"With the proliferation of automated systems for reliable and highly secure human authentication and identification, the importance of technological solutions in biometrics is growing along with security awareness. Indeed, conventional authentication methodologies, consisting of knowledge-based systems that make use of something you know (e.g., username and password) and token-based systems that make use of something you have (e.g., identification card), are not able to meet the strict requirements of reliable security applications. Conversely, biometric systems make use of behavioral (extrinsic) and/or physiological (intrinsic) human characteristics, overcoming the security issues affecting the conventional methods for personal authentication. This book chapter provides an overview of the most commonly used biometric traits along with their properties, the various biometric system operating modalities as well as various security aspects related to these systems. In particular, it will be discussed the different stages involved in a biometric recognition process and further discuss various threats that can be exploited to compromise the security of a biometric system. Finally, in order to evaluate the systems’ performance, metrics must be adopted. The most widely used metrics are, therefore, discussed in relation to the provided system accuracy and security, and applicability in real-world deployments.","PeriodicalId":180604,"journal":{"name":"Recent Advances in Biometrics [Working Title]","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121880885","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：