Pub Date : 2014-08-01DOI: 10.1109/ISBAST.2014.7013096
Selma Elnasir, S. Shamsuddin
Palm vein recognition is a new promising field in biometrics. The palm vein pattern provides highly discriminating features that are difficult to forge because it resides underneath the palmar skin. However, the issues of extracting the palm vein features and the high dimension of the feature space are still open. Therefore, in this paper, we propose an improved scheme of palm vein recognition method based on the Linear Discrimination Analysis (LDA) to extract the discriminative features with low dimension. LDA is later followed by the matching procedure using cosine distance nearest neighbor classifier. The performance of the proposed scheme produced 99.50% for identification rate, 100% for verification rate and 0.0% of Equal Error Rate (EER). The experiments prove that the proposed method has a better performance compared with Principal Component Analysis and Gabor filter methods.
{"title":"Proposed scheme for palm vein recognition based on Linear Discrimination Analysis and nearest neighbour classifier","authors":"Selma Elnasir, S. Shamsuddin","doi":"10.1109/ISBAST.2014.7013096","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013096","url":null,"abstract":"Palm vein recognition is a new promising field in biometrics. The palm vein pattern provides highly discriminating features that are difficult to forge because it resides underneath the palmar skin. However, the issues of extracting the palm vein features and the high dimension of the feature space are still open. Therefore, in this paper, we propose an improved scheme of palm vein recognition method based on the Linear Discrimination Analysis (LDA) to extract the discriminative features with low dimension. LDA is later followed by the matching procedure using cosine distance nearest neighbor classifier. The performance of the proposed scheme produced 99.50% for identification rate, 100% for verification rate and 0.0% of Equal Error Rate (EER). The experiments prove that the proposed method has a better performance compared with Principal Component Analysis and Gabor filter methods.","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123451367","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 : 2014-08-01DOI: 10.1109/ISBAST.2014.7013100
Syed Mohd Zahid Syed Zainal Ariffin, N. Jamil
Ear biometric is slowly gaining its position in biometric studies. Just like fingerprint and iris, the ears are unique and have other advantages over current regular biometric methods. Besides those advantages, there are some issues arising for ear recognition. One of those is regarding the illumination. Low illumination may result in low quality image acquired resulting in low recognition rate. Based on this situation, we proposed a cross-band ear recognition to overcome the variant illumination problem. This method starts by measuring the environments illumination which will determine which type of images (i.e.: thermal or visible) acquired to be processed. Once determined, the images will undergo pre-processing before the ear region is being localized using Viola-Jones approach with Haar-like feature. The ear features will be extracted using local binary patterns operator. Euclidean distance of the feature of test image and database images will be calculated. The lowest Euclidean value will determine the individual identity (intra- and inter-variance).
{"title":"Cross-band ear recognition in low or variant illumination environments","authors":"Syed Mohd Zahid Syed Zainal Ariffin, N. Jamil","doi":"10.1109/ISBAST.2014.7013100","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013100","url":null,"abstract":"Ear biometric is slowly gaining its position in biometric studies. Just like fingerprint and iris, the ears are unique and have other advantages over current regular biometric methods. Besides those advantages, there are some issues arising for ear recognition. One of those is regarding the illumination. Low illumination may result in low quality image acquired resulting in low recognition rate. Based on this situation, we proposed a cross-band ear recognition to overcome the variant illumination problem. This method starts by measuring the environments illumination which will determine which type of images (i.e.: thermal or visible) acquired to be processed. Once determined, the images will undergo pre-processing before the ear region is being localized using Viola-Jones approach with Haar-like feature. The ear features will be extracted using local binary patterns operator. Euclidean distance of the feature of test image and database images will be calculated. The lowest Euclidean value will determine the individual identity (intra- and inter-variance).","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130951741","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 : 2014-08-01DOI: 10.1109/ISBAST.2014.7013084
X. Chen, Wen Li, Zengli Liu, Zaihong Zhou
As biometric vector may not follow the Gaussian distribution under complex light, pose and accessories, systems often yield unacceptable performance when subjected to impulsive, non-Gaussian noise. This paper adopts signal symmetric alpha stable distribution theory to construct fractional low-order independent component analysis algorithm (FLOD-ICA) and applied FLOD-ICA to solve the partial occlusion face recognition problem. Experiments verified that our proposed scheme is effective for face recognition under partial occlusion.
{"title":"Fractional low-order independent component analysis for face recognition robust to partial occlusion","authors":"X. Chen, Wen Li, Zengli Liu, Zaihong Zhou","doi":"10.1109/ISBAST.2014.7013084","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013084","url":null,"abstract":"As biometric vector may not follow the Gaussian distribution under complex light, pose and accessories, systems often yield unacceptable performance when subjected to impulsive, non-Gaussian noise. This paper adopts signal symmetric alpha stable distribution theory to construct fractional low-order independent component analysis algorithm (FLOD-ICA) and applied FLOD-ICA to solve the partial occlusion face recognition problem. Experiments verified that our proposed scheme is effective for face recognition under partial occlusion.","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"577 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133947911","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 : 2014-08-01DOI: 10.1109/ISBAST.2014.7013085
X. Chen, Luping Zheng, Zengli Liu, Jiashu Zhang
In this paper, we propose a matrix random low-rank approximation (MRLRA) approach to generate cancelable biometric templates for privacy-preserving. MRLRA constructs a random low-rank matrix to approximate the hybridization of biometric feature and a random matrix. Theoretically analysis shows the distance between one cancelable low-rank biometric template by MRLRA and its original template is very small, which results to the verification and authentication performance by MRLRA is near that of original templates. Cancelable biometric templates by MRLRA conquer the weakness of random projection based cancelable biometric templates, in which the performance will deteriorate much under the same tokens. Experiments have verified that (i) cancelable biometric templates by MRLRA are sensitive to the user-specific tokens which are used for constructing the random matrix in MRLRA; (ii) MRLRA can reduce the noise of biometric templates; (iii)Even under the condition of same tokens, the performance of cancelable biometric templates by MRLRA doesn't deteriorate much.
{"title":"Privacy-preserving biometrics using matrix random low-rank approximation approach","authors":"X. Chen, Luping Zheng, Zengli Liu, Jiashu Zhang","doi":"10.1109/ISBAST.2014.7013085","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013085","url":null,"abstract":"In this paper, we propose a matrix random low-rank approximation (MRLRA) approach to generate cancelable biometric templates for privacy-preserving. MRLRA constructs a random low-rank matrix to approximate the hybridization of biometric feature and a random matrix. Theoretically analysis shows the distance between one cancelable low-rank biometric template by MRLRA and its original template is very small, which results to the verification and authentication performance by MRLRA is near that of original templates. Cancelable biometric templates by MRLRA conquer the weakness of random projection based cancelable biometric templates, in which the performance will deteriorate much under the same tokens. Experiments have verified that (i) cancelable biometric templates by MRLRA are sensitive to the user-specific tokens which are used for constructing the random matrix in MRLRA; (ii) MRLRA can reduce the noise of biometric templates; (iii)Even under the condition of same tokens, the performance of cancelable biometric templates by MRLRA doesn't deteriorate much.","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115798944","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 : 2014-08-01DOI: 10.1109/ISBAST.2014.7013099
Cynthia S. Mlambo, F. Nelwamondo, M. E. Mathekga
In this paper, two effective and mostly used Hough Transform (HT) based fingerprint alignment approaches are compared, namely; Local Match Based Alignment (LMBA) and Discretized Rotation Based Alignment (DRBA). The comparison was performed by considering different conditions of minutiae points, which are rotation, translation and the number of minutiae points. In addition, this research reports the advantages of understanding the quality and relationships between the wide varieties of existing HT based fingerprint alignment methods. Minutiae points extracted from fingerprints of FVC2000 database were used on the experiments to compare these approaches. The results revealed that LMBA approach performs better than the DRBA approach on minutiae points set with larger rotation and small number of points. The DRBA approach was found to perform better with minutiae points with large amount of translation, and the computational time was less than that of LMBA approach. However, the memory usage required in DRBA is greater than memory required in LMBA.
{"title":"Comparison of effective hough transform-based fingerprint alignment approaches","authors":"Cynthia S. Mlambo, F. Nelwamondo, M. E. Mathekga","doi":"10.1109/ISBAST.2014.7013099","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013099","url":null,"abstract":"In this paper, two effective and mostly used Hough Transform (HT) based fingerprint alignment approaches are compared, namely; Local Match Based Alignment (LMBA) and Discretized Rotation Based Alignment (DRBA). The comparison was performed by considering different conditions of minutiae points, which are rotation, translation and the number of minutiae points. In addition, this research reports the advantages of understanding the quality and relationships between the wide varieties of existing HT based fingerprint alignment methods. Minutiae points extracted from fingerprints of FVC2000 database were used on the experiments to compare these approaches. The results revealed that LMBA approach performs better than the DRBA approach on minutiae points set with larger rotation and small number of points. The DRBA approach was found to perform better with minutiae points with large amount of translation, and the computational time was less than that of LMBA approach. However, the memory usage required in DRBA is greater than memory required in LMBA.","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"67 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131916868","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 : 2014-08-01DOI: 10.1109/ISBAST.2014.7013115
Yuan Tian, Mznah Al-Rodhaan, Biao Song, A. Al-Dhelaan, Tinghuai Ma
Homomorphic encryption has become a popular research topic since the cloud computing paradigm emerged. This paper discusses the design of a GPU-assisted homomorphic cryptograph for matrix operation. Our proposed scheme is based on an n*n matrix multiplication which are computationally homomorphic. We use more efficient GPU programming scheme with the extension of DGHV homomorphism, which prove the result of verification does not leak any information about the inputs or the output during the encryption and decryption. The performance results are obtained from the executions on a machine equipped with a GeForce GTX 765M GPU. We use three basic parallel algorithms to form efficient solutions which accelerate the speed of encryption and evaluation. Although fully homomorphic encryption is still not practical for real world applications in current stage, this work shows the possibility to improve the performance of homomorphic encryption and achieve this target one step closer.
{"title":"Somewhat homomorphic cryptography for matrix multiplication using GPU acceleration","authors":"Yuan Tian, Mznah Al-Rodhaan, Biao Song, A. Al-Dhelaan, Tinghuai Ma","doi":"10.1109/ISBAST.2014.7013115","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013115","url":null,"abstract":"Homomorphic encryption has become a popular research topic since the cloud computing paradigm emerged. This paper discusses the design of a GPU-assisted homomorphic cryptograph for matrix operation. Our proposed scheme is based on an n*n matrix multiplication which are computationally homomorphic. We use more efficient GPU programming scheme with the extension of DGHV homomorphism, which prove the result of verification does not leak any information about the inputs or the output during the encryption and decryption. The performance results are obtained from the executions on a machine equipped with a GeForce GTX 765M GPU. We use three basic parallel algorithms to form efficient solutions which accelerate the speed of encryption and evaluation. Although fully homomorphic encryption is still not practical for real world applications in current stage, this work shows the possibility to improve the performance of homomorphic encryption and achieve this target one step closer.","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129654084","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 : 2014-08-01DOI: 10.1109/ISBAST.2014.7013124
Hiba Zuhair Zeydan, A. Selamat, M. Salleh
Phishers have been continually changed their tricks and emerged novel variants for more security violations and causes of monetary losses in business organizations. The lack of existing anti-phishing solutions considered as an optimum anti-phishing is because of detection incapability specifically against novel phishes. This paper classifies the existing anti-phishing tools, identifies their detection incapability against several kinds of novel phishes and underscores the issues behind this problem. Further it suggests next wave of research to solve it. Targeting academic and industry researchers, this paper provide a valuable source of information to contribute the cyberspace with new products and fulfill the security flaws.
{"title":"Survey of anti-phishing tools with detection capabilities","authors":"Hiba Zuhair Zeydan, A. Selamat, M. Salleh","doi":"10.1109/ISBAST.2014.7013124","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013124","url":null,"abstract":"Phishers have been continually changed their tricks and emerged novel variants for more security violations and causes of monetary losses in business organizations. The lack of existing anti-phishing solutions considered as an optimum anti-phishing is because of detection incapability specifically against novel phishes. This paper classifies the existing anti-phishing tools, identifies their detection incapability against several kinds of novel phishes and underscores the issues behind this problem. Further it suggests next wave of research to solve it. Targeting academic and industry researchers, this paper provide a valuable source of information to contribute the cyberspace with new products and fulfill the security flaws.","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115253619","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：