Pub Date : 2014-08-01DOI: 10.1109/ISBAST.2014.7013128
Syed Zainudeen Mohd Shaid, M. A. Maarof
Several methods have been devised by researchers to facilitate malware analysis and one of them is through malware visualization. Malware visualization is a field that focuses on representing malware features in a form of visual cues that could be used to convey more information about a particular malware. There has been works in malware visualization but unfortunately, there seems to be a lack of focus in visualizing malware behavior. In this paper, we highlight our findings in visualizing malware behavior and its potential benefit for malware classification. Our research shows that malware behavior visualization can be used as a way to identify malware variants with high accuracy.
{"title":"Malware behavior image for malware variant identification","authors":"Syed Zainudeen Mohd Shaid, M. A. Maarof","doi":"10.1109/ISBAST.2014.7013128","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013128","url":null,"abstract":"Several methods have been devised by researchers to facilitate malware analysis and one of them is through malware visualization. Malware visualization is a field that focuses on representing malware features in a form of visual cues that could be used to convey more information about a particular malware. There has been works in malware visualization but unfortunately, there seems to be a lack of focus in visualizing malware behavior. In this paper, we highlight our findings in visualizing malware behavior and its potential benefit for malware classification. Our research shows that malware behavior visualization can be used as a way to identify malware variants with high accuracy.","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"25 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":"127767993","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.2014.7013123
Muhammad Syafiq Samsi, S. Razak
As use of the internet has become wide spread, many good effects are seen but the adverse functions are also found. One of these adverse functions is the unnecessary personal information exposure. This issue may be a significant problem because there is the potential for so many people to see the information if the information is disclosed by mistake by its collector such as internet service provider. Information can also be disclosed by the person who holds a superior role in the system, namely, the system administrator. Internet users have paid special attention to this issue caused by the fact that many of the operations and transactions that they carry out through the internet can be easily recorded and collected. Thus, identity disintegration has become a desirable feature to be implemented in a database management system. In this paper, we propose an identity disintegration mechanism that is intended for use in the healthcare field.
{"title":"A mechanism for privacy preserving in healthcare organizations","authors":"Muhammad Syafiq Samsi, S. Razak","doi":"10.1109/ISBAST.2014.7013123","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013123","url":null,"abstract":"As use of the internet has become wide spread, many good effects are seen but the adverse functions are also found. One of these adverse functions is the unnecessary personal information exposure. This issue may be a significant problem because there is the potential for so many people to see the information if the information is disclosed by mistake by its collector such as internet service provider. Information can also be disclosed by the person who holds a superior role in the system, namely, the system administrator. Internet users have paid special attention to this issue caused by the fact that many of the operations and transactions that they carry out through the internet can be easily recorded and collected. Thus, identity disintegration has become a desirable feature to be implemented in a database management system. In this paper, we propose an identity disintegration mechanism that is intended for use in the healthcare field.","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"194 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":"115985400","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.2014.7013089
M. Z. Osman, M. A. Maarof, M. F. Rohani
Skin colour detection is widely used in applications such as adult image filtering, steganography, content-based image retrieval (CBIR), face tracking, face recognition, and facial surgery. Recently, researchers are more interested in developing high level skin detection strategy for still images based on online sample learning approach which requires no offline training dataset. Previous dynamic skin color detection works has shown high true positive result than the static skin detection in term of skin-like colour and ethnicity factors. However, dynamic skin colour detection also produced high false positives result which lowers the accuracy of skin detection. This is due to the current approach of elliptical mask model that is not flexible for face rotation and is based on single colour space. Therefore, we propose dynamic skin colour detection based on multi-colour space. The result shows the effectiveness of the proposed method by reducing the false positive rate from 19.6069% to 6.9887% and increased the precision rate from 81.27% to 91.49%.
{"title":"Improved skin detection based on dynamic threshold using multi-colour space","authors":"M. Z. Osman, M. A. Maarof, M. F. Rohani","doi":"10.1109/ISBAST.2014.7013089","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013089","url":null,"abstract":"Skin colour detection is widely used in applications such as adult image filtering, steganography, content-based image retrieval (CBIR), face tracking, face recognition, and facial surgery. Recently, researchers are more interested in developing high level skin detection strategy for still images based on online sample learning approach which requires no offline training dataset. Previous dynamic skin color detection works has shown high true positive result than the static skin detection in term of skin-like colour and ethnicity factors. However, dynamic skin colour detection also produced high false positives result which lowers the accuracy of skin detection. This is due to the current approach of elliptical mask model that is not flexible for face rotation and is based on single colour space. Therefore, we propose dynamic skin colour detection based on multi-colour space. The result shows the effectiveness of the proposed method by reducing the false positive rate from 19.6069% to 6.9887% and increased the precision rate from 81.27% to 91.49%.","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"2 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":"114486011","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}
Biometric data is non-renewable and irrevocable, so it is necessary to encrypt in the process of collection, storage and transmission to preserve its security. In this paper, a lightweight block cipher applied in the resource-limited environment is proposed by combining generalized Feistel network with chaotic maps. The cipher employs linear mixing transformations within encryption operation and adopts round keys from chaotic systems. Theoretical analysis and experimental results indicate that the cipher provides fast diffusion speed and high security.
{"title":"A lightweight blockcipher based on chaotic maps","authors":"Wenyang Liu, Xiaomin Wang, Wenfang Zhang, Xianfeng Guo","doi":"10.1109/ISBAST.2014.7013112","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013112","url":null,"abstract":"Biometric data is non-renewable and irrevocable, so it is necessary to encrypt in the process of collection, storage and transmission to preserve its security. In this paper, a lightweight block cipher applied in the resource-limited environment is proposed by combining generalized Feistel network with chaotic maps. The cipher employs linear mixing transformations within encryption operation and adopts round keys from chaotic systems. Theoretical analysis and experimental results indicate that the cipher provides fast diffusion speed and high security.","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"54 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":"126495613","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.2014.7013108
Natasha Arjumand Shoaib Mirza, Haider Abbas, F. A. Khan, J. Al-Muhtadi
Information and communication security has gained significant importance due to its wide spread use, increased sophistication and complexity in its deployment. On the other hand, more sophisticated and stealthy techniques are being practiced by the intruder's group to penetrate and exploit the technology and attack detection. One such treacherous threat to all critical assets of an organization is Advanced Persistent Threat (APT). Since APT attack vector is not previously known, consequently this can harm the organization's assets before the patch for this security flaw is released/available. This paper presents a preliminary research effort to counter the APT or zero day attacks at an early stage by detecting malwares. Open Source version of Security Information and Event Management (SIEM) is used to detect denial of service attack launched through remote desktop service. The framework presented in this paper also shows the efficiency of the technique and it can be enhanced with more sophisticated mechanisms for APT attack detection.
信息和通信安全由于其广泛的使用，其部署的复杂性和复杂性日益增加而变得非常重要。另一方面，入侵者组织正在使用更复杂和隐蔽的技术来渗透和利用技术和攻击检测。高级持续威胁(APT)是对组织所有关键资产的一种危险威胁。由于以前不知道APT攻击向量，因此在此安全漏洞的补丁发布/可用之前，这可能会损害组织的资产。本文介绍了通过检测恶意软件在早期阶段对抗APT或零日攻击的初步研究工作。SIEM (Security Information and Event Management)是开源版本，用于检测通过远程桌面服务发起的拒绝服务攻击。本文提出的框架也显示了该技术的效率，并且可以通过更复杂的APT攻击检测机制来增强它。
{"title":"Anticipating Advanced Persistent Threat (APT) countermeasures using collaborative security mechanisms","authors":"Natasha Arjumand Shoaib Mirza, Haider Abbas, F. A. Khan, J. Al-Muhtadi","doi":"10.1109/ISBAST.2014.7013108","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013108","url":null,"abstract":"Information and communication security has gained significant importance due to its wide spread use, increased sophistication and complexity in its deployment. On the other hand, more sophisticated and stealthy techniques are being practiced by the intruder's group to penetrate and exploit the technology and attack detection. One such treacherous threat to all critical assets of an organization is Advanced Persistent Threat (APT). Since APT attack vector is not previously known, consequently this can harm the organization's assets before the patch for this security flaw is released/available. This paper presents a preliminary research effort to counter the APT or zero day attacks at an early stage by detecting malwares. Open Source version of Security Information and Event Management (SIEM) is used to detect denial of service attack launched through remote desktop service. The framework presented in this paper also shows the efficiency of the technique and it can be enhanced with more sophisticated mechanisms for APT attack detection.","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"44 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":"132969452","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.2014.7013097
Ali Sharifara, M. Rahim, Yasaman Anisi
Face detection is an interesting area in research application of computer vision and pattern recognition, especially during the past several years. It is also plays a vital role in surveillance systems which is the first steps in face recognition systems. The high degree of variation in the appearance of human faces causes the face detection as a complex problem in computer vision. The face detection systems aimed to decrease false positive rate and increase the accuracy of detecting face especially in complex background images. The main aim of this paper is to present an up-to-date review of face detection methods including feature-based, appearance-based, knowledge-based and template matching. Also, the study presents the effect of applying Haar-like features along with neural networks. We also conclude this paper with some discussions on how the work can be taken further.
{"title":"A general review of human face detection including a study of neural networks and Haar feature-based cascade classifier in face detection","authors":"Ali Sharifara, M. Rahim, Yasaman Anisi","doi":"10.1109/ISBAST.2014.7013097","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013097","url":null,"abstract":"Face detection is an interesting area in research application of computer vision and pattern recognition, especially during the past several years. It is also plays a vital role in surveillance systems which is the first steps in face recognition systems. The high degree of variation in the appearance of human faces causes the face detection as a complex problem in computer vision. The face detection systems aimed to decrease false positive rate and increase the accuracy of detecting face especially in complex background images. The main aim of this paper is to present an up-to-date review of face detection methods including feature-based, appearance-based, knowledge-based and template matching. Also, the study presents the effect of applying Haar-like features along with neural networks. We also conclude this paper with some discussions on how the work can be taken further.","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"8 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":"133029297","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.2014.7013093
Sisanda Makinana, J. V. D. Merwe, T. Malumedzha
Iris recognition systems have attracted much attention for their uniqueness, stability and reliability. However, performance of this system depends on quality of acquired iris sample. This is because in order to obtain reliable features good quality images are to be used. Thus, it is important to accurately assess image quality before applying feature extraction algorithm in order to avoid insufficient results. This study aims to quantitatively analyse the effect of iris image quality in order to ensure that good quality images are selected for feature extraction, in order to improve iris recognition system. In addition, this research proposes a measure of iris image quality using a Fourier Transform. The experimental results demonstrate that the proposed algorithm shows better performance in quality classification as it yields a 97% accuracy rate than the existing algorithms.
{"title":"A fourier transform quality measure for iris images","authors":"Sisanda Makinana, J. V. D. Merwe, T. Malumedzha","doi":"10.1109/ISBAST.2014.7013093","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013093","url":null,"abstract":"Iris recognition systems have attracted much attention for their uniqueness, stability and reliability. However, performance of this system depends on quality of acquired iris sample. This is because in order to obtain reliable features good quality images are to be used. Thus, it is important to accurately assess image quality before applying feature extraction algorithm in order to avoid insufficient results. This study aims to quantitatively analyse the effect of iris image quality in order to ensure that good quality images are selected for feature extraction, in order to improve iris recognition system. In addition, this research proposes a measure of iris image quality using a Fourier Transform. The experimental results demonstrate that the proposed algorithm shows better performance in quality classification as it yields a 97% accuracy rate than the existing algorithms.","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"82 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":"134363620","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.2014.7013141
A. Jama, M. M. Siraj, R. Kadir
Information technology and information system have been used widely in many fields such as in business, education, marketing, transportation and medical. Security aspect plays a vital role and thus turns into a challenging issue. The security should be readily installed and resistance to various numbers of potential attacks likes Spyware, Phishing / Spam and Malwares (Virus, Worm and Trojans). It is important to have specific countermeasures that could minimize the harm to enterprises. Thus, increasing the awareness to optimal level is the main target of enterprise management. Unfortunately, the main reason that fails many existing enterprise' Information Security Awareness Management (ISAM) models is the complexity and inflexibility. Complexity means the model's structure is less practical (for instance, the implementation needs to be deployed manually). Inflexibility means it cannot support multiple kinds of businesses and did not consider security aspects. In this paper, we surveyed and discussed several existing ISAM models considering the security issues in current enterprise. We proposed a metamodel-based approach for ISAM that can offer efficiency and security that brings out clearly significant benefits by highlighting the organization overall level of awareness whether it is strong enough or weak. This will help many users in this domain to easily understand the important concepts required for their own information security awareness management.
{"title":"Towards metamodel-based approach for Information Security Awareness Management","authors":"A. Jama, M. M. Siraj, R. Kadir","doi":"10.1109/ISBAST.2014.7013141","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013141","url":null,"abstract":"Information technology and information system have been used widely in many fields such as in business, education, marketing, transportation and medical. Security aspect plays a vital role and thus turns into a challenging issue. The security should be readily installed and resistance to various numbers of potential attacks likes Spyware, Phishing / Spam and Malwares (Virus, Worm and Trojans). It is important to have specific countermeasures that could minimize the harm to enterprises. Thus, increasing the awareness to optimal level is the main target of enterprise management. Unfortunately, the main reason that fails many existing enterprise' Information Security Awareness Management (ISAM) models is the complexity and inflexibility. Complexity means the model's structure is less practical (for instance, the implementation needs to be deployed manually). Inflexibility means it cannot support multiple kinds of businesses and did not consider security aspects. In this paper, we surveyed and discussed several existing ISAM models considering the security issues in current enterprise. We proposed a metamodel-based approach for ISAM that can offer efficiency and security that brings out clearly significant benefits by highlighting the organization overall level of awareness whether it is strong enough or weak. This will help many users in this domain to easily understand the important concepts required for their own information security awareness management.","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"4 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":"125301070","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.2014.7013131
Biao Song, Yuan Tian, Bingyin Zhou
Cloud based video surveillance systems have been proposed and implemented recently. With the advances in cloud technologies, opportunity for getting on-demand remote video surveillance service can be pursued. In this paper, we propose a novel remote display solution that allows remote surveillance users to watch real-time surveillance video, to use surveillance software and to share screen updates among users on remote desktop. Multiple encoders and parallel encoding method are adopted in remote display to meet quality of service requirement under varying situations. Our proposed system deals with dynamic workload better than traditional remote display methods since surveillance task and encoding task are separately managed. Two queuing models are designed to handle resource provisioning problem for different encoders.
{"title":"Design and Evaluation of Remote Video Surveillance System on Private Cloud","authors":"Biao Song, Yuan Tian, Bingyin Zhou","doi":"10.1109/ISBAST.2014.7013131","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013131","url":null,"abstract":"Cloud based video surveillance systems have been proposed and implemented recently. With the advances in cloud technologies, opportunity for getting on-demand remote video surveillance service can be pursued. In this paper, we propose a novel remote display solution that allows remote surveillance users to watch real-time surveillance video, to use surveillance software and to share screen updates among users on remote desktop. Multiple encoders and parallel encoding method are adopted in remote display to meet quality of service requirement under varying situations. Our proposed system deals with dynamic workload better than traditional remote display methods since surveillance task and encoding task are separately managed. Two queuing models are designed to handle resource provisioning problem for different encoders.","PeriodicalId":292333,"journal":{"name":"2014 International Symposium on Biometrics and Security Technologies (ISBAST)","volume":"17 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":"125117914","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.2014.7013087
Hengjian Li, J. Dong, Jinping Li
To make use of information contained in the null space of withinclass during the implementation of discriminant locality preserving projection(DLPP), a very efficient feature extraction algorithm called two-dimensional direct discriminant LPP (2D-DDLPP) algorithm is proposed for face recognition in this paper. By modifying the simultaneous diagonalization procedure, the null space of the interclass matrix can be discarded for it carries no discriminative information and the null space of intraclass matrix is preserved for it contains very important information for classification. Also, the 2D-DDLPP algorithm does not need to transform 2D image matrix into a vector prior to feature extraction so that it can be implemented more efficient and accurate than the 1D traditional in extracting the facial features. Therefore, the performance of 2D-DDLPP has been greatly improved. Extensive experiments are performed to test and evaluate the new algorithm using the UMIST and the AR face databases. The experimental results indicate that our proposed 2D DDLPP method is not only computationally more efficiently but also more accurate than the 2DLPP method in extracting the facial features for face recognition.
{"title":"Two-dimensional direct discriminant locality preserving projection analysis for face recognition","authors":"Hengjian Li, J. Dong, Jinping Li","doi":"10.1109/ISBAST.2014.7013087","DOIUrl":"https://doi.org/10.1109/ISBAST.2014.7013087","url":null,"abstract":"To make use of information contained in the null space of withinclass during the implementation of discriminant locality preserving projection(DLPP), a very efficient feature extraction algorithm called two-dimensional direct discriminant LPP (2D-DDLPP) algorithm is proposed for face recognition in this paper. By modifying the simultaneous diagonalization procedure, the null space of the interclass matrix can be discarded for it carries no discriminative information and the null space of intraclass matrix is preserved for it contains very important information for classification. Also, the 2D-DDLPP algorithm does not need to transform 2D image matrix into a vector prior to feature extraction so that it can be implemented more efficient and accurate than the 1D traditional in extracting the facial features. Therefore, the performance of 2D-DDLPP has been greatly improved. Extensive experiments are performed to test and evaluate the new algorithm using the UMIST and the AR face databases. The experimental results indicate that our proposed 2D DDLPP method is not only computationally more efficiently but also more accurate than the 2DLPP method in extracting the facial features for face recognition.","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":"126350130","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：