Pub Date : 2008-09-09DOI: 10.1109/UKRICIS.2008.4798933
K. C. Lim, M. Boissenin, B. Amavasai, R. Saatchi
This paper discusses the development of a freehand 3-D surface reconstruction system. The system was constructed by making use of readily available off-the-shelf components, namely a laser line emitter and a webcam. The 3-D laser scanner system allows the user to hand sweep the laser line across the object to be scanned. The 3-D surface information of the object is captured as follows. A series of digital images of the laser line, generated by the intersection of the laser plane, the surface of the object and the background planar object were captured and stored in a PC. The points on the laser line were extracted. The 2-D laser points that were found on the surface of the planar object were projected onto the 3-D space using a pinhole camera model. The laser plane was calibrated. Using the 2-D laser points found on the surface of the 3-D object, a cloud of 3-D points which represent the surface of the object being scanned was generated by triangulation. For the laser plane calibration two different methods were implemented. Their performance were compared.
{"title":"Development of a desktop freehand 3-D surface reconstruction system","authors":"K. C. Lim, M. Boissenin, B. Amavasai, R. Saatchi","doi":"10.1109/UKRICIS.2008.4798933","DOIUrl":"https://doi.org/10.1109/UKRICIS.2008.4798933","url":null,"abstract":"This paper discusses the development of a freehand 3-D surface reconstruction system. The system was constructed by making use of readily available off-the-shelf components, namely a laser line emitter and a webcam. The 3-D laser scanner system allows the user to hand sweep the laser line across the object to be scanned. The 3-D surface information of the object is captured as follows. A series of digital images of the laser line, generated by the intersection of the laser plane, the surface of the object and the background planar object were captured and stored in a PC. The points on the laser line were extracted. The 2-D laser points that were found on the surface of the planar object were projected onto the 3-D space using a pinhole camera model. The laser plane was calibrated. Using the 2-D laser points found on the surface of the 3-D object, a cloud of 3-D points which represent the surface of the object being scanned was generated by triangulation. For the laser plane calibration two different methods were implemented. Their performance were compared.","PeriodicalId":311925,"journal":{"name":"2008 7th IEEE International Conference on Cybernetic Intelligent Systems","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127171357","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 : 2008-09-01DOI: 10.1109/UKRICIS.2008.4798935
F. Majidi, H. Mirzaei, T. Iranpour, F. Foroughi
Vulnerabilities in common security components such as firewalls are inevitable. Intrusion Detection Systems (IDS) are used as another wall to protect computer systems and to identify corresponding vulnerabilities. This paper presents a new ensemble-based method for intrusion detection. This method uses feature transformation to create the needed diversity between base classifiers. In other words, first different sets of features are created by mapping the original features into new spaces where the samples are well separated, and then each base classifier is trained on one of these newly created features sets. The proposed method for constructing an ensemble of classifiers is a general method which may be used in any classification problem. KDD-99 dataset is used to evaluate the proposed method and the results are compared with some recent works in the literature using the same dataset. The results of comparing the performance of the proposed method with other alternative classification methods are encouraging.
{"title":"A diversity creation method for ensemble based classification: Application in intrusion detection","authors":"F. Majidi, H. Mirzaei, T. Iranpour, F. Foroughi","doi":"10.1109/UKRICIS.2008.4798935","DOIUrl":"https://doi.org/10.1109/UKRICIS.2008.4798935","url":null,"abstract":"Vulnerabilities in common security components such as firewalls are inevitable. Intrusion Detection Systems (IDS) are used as another wall to protect computer systems and to identify corresponding vulnerabilities. This paper presents a new ensemble-based method for intrusion detection. This method uses feature transformation to create the needed diversity between base classifiers. In other words, first different sets of features are created by mapping the original features into new spaces where the samples are well separated, and then each base classifier is trained on one of these newly created features sets. The proposed method for constructing an ensemble of classifiers is a general method which may be used in any classification problem. KDD-99 dataset is used to evaluate the proposed method and the results are compared with some recent works in the literature using the same dataset. The results of comparing the performance of the proposed method with other alternative classification methods are encouraging.","PeriodicalId":311925,"journal":{"name":"2008 7th IEEE International Conference on Cybernetic Intelligent Systems","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124733797","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 : 2008-09-01DOI: 10.1109/UKRICIS.2008.4798938
M. Akhlaghinia, Ahmad Lotfi, C. Langensiepen, N. Sherkat
In this paper, the simulation of an occupant's behaviour in a single-occupant ambient intelligent environment is addressed. The algorithm of the simulator is designed flexible enough to accept different environmental profiles including the number of areas and the connections between them along with different occupant's profiles including expected daily occupancy pattern of him/her and the uncertainty of his/her behaviour to follow this occupancy pattern. The generated occupancy signal by the simulator represents the occupancy of areas by assuming a signal level for the occupancy of each area in a single-occupant environment with the resolution of one minute in a whole day activity of the occupant in the environment. The validity of the simulator will be verified by tuning the simulator's parameters to occupancy data collected by sensory agents from a real equivalent environment. By applying the generated data from this simulator to the data mining techniques, the ability of different techniques will be investigated.
{"title":"Occupancy simulator for a single-occupant ambient intelligent environment","authors":"M. Akhlaghinia, Ahmad Lotfi, C. Langensiepen, N. Sherkat","doi":"10.1109/UKRICIS.2008.4798938","DOIUrl":"https://doi.org/10.1109/UKRICIS.2008.4798938","url":null,"abstract":"In this paper, the simulation of an occupant's behaviour in a single-occupant ambient intelligent environment is addressed. The algorithm of the simulator is designed flexible enough to accept different environmental profiles including the number of areas and the connections between them along with different occupant's profiles including expected daily occupancy pattern of him/her and the uncertainty of his/her behaviour to follow this occupancy pattern. The generated occupancy signal by the simulator represents the occupancy of areas by assuming a signal level for the occupancy of each area in a single-occupant environment with the resolution of one minute in a whole day activity of the occupant in the environment. The validity of the simulator will be verified by tuning the simulator's parameters to occupancy data collected by sensory agents from a real equivalent environment. By applying the generated data from this simulator to the data mining techniques, the ability of different techniques will be investigated.","PeriodicalId":311925,"journal":{"name":"2008 7th IEEE International Conference on Cybernetic Intelligent Systems","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123282994","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 : 2008-09-01DOI: 10.1109/UKRICIS.2008.4798932
H. O. Latif, N. Sherkat, Ahmad Lotfi
Most teleoperation tasks involve controlling as well as monitoring from a remote location. This requires the eyes of the operator to be engaged in the monitoring task and the hands in the controlling task for the whole duration of the operation. Since the eyes are involved in the monitoring task anyway, inputs from their gaze can be used to aid in the controlling task to free the hands of the operator from this task. However, the challenge here lies in distinguishing between the inputs that should be used for monitoring and those that should be used for controlling. To address this challenge, this paper presents a novel means of developing a teleoperation interface through eye gaze. The interface developed in this work, which is called the TeleGaze interface for short, enables the operator to monitor as well as control a mobile robot remotely through the use of the eyes only. The TeleGaze interface is developed out of two different designs based on user satisfaction. A task oriented evaluation for the TeleGaze interface is conducted in comparison with other interaction modalities. The evaluation shows promising results towards TeleGaze as an aid in human-robot interaction.
{"title":"TeleGaze: Teleoperation through eye gaze","authors":"H. O. Latif, N. Sherkat, Ahmad Lotfi","doi":"10.1109/UKRICIS.2008.4798932","DOIUrl":"https://doi.org/10.1109/UKRICIS.2008.4798932","url":null,"abstract":"Most teleoperation tasks involve controlling as well as monitoring from a remote location. This requires the eyes of the operator to be engaged in the monitoring task and the hands in the controlling task for the whole duration of the operation. Since the eyes are involved in the monitoring task anyway, inputs from their gaze can be used to aid in the controlling task to free the hands of the operator from this task. However, the challenge here lies in distinguishing between the inputs that should be used for monitoring and those that should be used for controlling. To address this challenge, this paper presents a novel means of developing a teleoperation interface through eye gaze. The interface developed in this work, which is called the TeleGaze interface for short, enables the operator to monitor as well as control a mobile robot remotely through the use of the eyes only. The TeleGaze interface is developed out of two different designs based on user satisfaction. A task oriented evaluation for the TeleGaze interface is conducted in comparison with other interaction modalities. The evaluation shows promising results towards TeleGaze as an aid in human-robot interaction.","PeriodicalId":311925,"journal":{"name":"2008 7th IEEE International Conference on Cybernetic Intelligent Systems","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122494855","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 : 2008-09-01DOI: 10.1109/UKRICIS.2008.4798966
F. Stubbs, J. St. Quinton, K. Grindley
Systematics is a specification language designed for automatic code generation. Systematics uniquely provides auto-provability by virtue of the inclusion of ldquosystem timerdquo as an inherent characteristic of information. A code generator based on Systematics is described which, unlike other code generators, requires no computing expertise on the part of the user, and is not limited to any specific type of generated application. The generator stores the specification in tabular form, in terms of 8 basic concepts. The generated system includes a pre-written ldquoauto-navigationrdquo function which is called to produce outputs on receipt of stimuli. The Systematics generator has initially been implemented in Microsoft Access to provide ldquoProof of Principlerdquo. A generic version of the Systematics Generator is currently being developed by the Systematics Research Group. This version will be independent of any proprietary database product, but with the ability to ldquofront-endrdquo any such product, and will also allow automatic optimisation of the database.
Systematics是一种为自动代码生成而设计的规范语言。Systematics独特地提供了自动可证明性，因为它包含了系统时间作为信息的固有特征。本文描述了一个基于Systematics的代码生成器，与其他代码生成器不同，它不需要用户的计算专业知识，也不局限于生成的任何特定类型的应用程序。生成器根据8个基本概念以表格形式存储规范。生成的系统包括一个预先编写的ldquoauto-navigationrdquo函数，该函数用于在接收刺激时产生输出。Systematics生成器最初已经在Microsoft Access中实现，以提供ldquoProof of principledquo。系统学研究小组目前正在开发系统学生成器的通用版本。这个版本将独立于任何专有的数据库产品，但有能力预先安装任何此类产品，并且还将允许数据库的自动优化。
{"title":"A Systematics generator","authors":"F. Stubbs, J. St. Quinton, K. Grindley","doi":"10.1109/UKRICIS.2008.4798966","DOIUrl":"https://doi.org/10.1109/UKRICIS.2008.4798966","url":null,"abstract":"Systematics is a specification language designed for automatic code generation. Systematics uniquely provides auto-provability by virtue of the inclusion of ldquosystem timerdquo as an inherent characteristic of information. A code generator based on Systematics is described which, unlike other code generators, requires no computing expertise on the part of the user, and is not limited to any specific type of generated application. The generator stores the specification in tabular form, in terms of 8 basic concepts. The generated system includes a pre-written ldquoauto-navigationrdquo function which is called to produce outputs on receipt of stimuli. The Systematics generator has initially been implemented in Microsoft Access to provide ldquoProof of Principlerdquo. A generic version of the Systematics Generator is currently being developed by the Systematics Research Group. This version will be independent of any proprietary database product, but with the ability to ldquofront-endrdquo any such product, and will also allow automatic optimisation of the database.","PeriodicalId":311925,"journal":{"name":"2008 7th IEEE International Conference on Cybernetic Intelligent Systems","volume":"270 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122084462","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 : 2008-09-01DOI: 10.1109/UKRICIS.2008.4798929
N. Khalifa, Anthony S. White, A. Elsayed
Leading firms face various challenges to increase their productivity, reduce costs and improve product quality while improving their profitability. That's why full-package producer have placed each operation in the most cost-effective location. Developing countries have played important role in that. Leading firms have been tempted to locate their manufacturing unit in the developing countries. Competitive material prices and reduced labour costs are main factors, which enable low-income developing countries to enter these global supply chains. This highlights the importance of production capabilities and resource that should be available in these countries. The main objective of this paper is to investigate the challenges that face implementing successful supply chains in these countries. The paper has investigated case studies from different industries to highlight on the common factors that lead to current supply chain deficiencies. As conclusion, the paper proposed a framework indicates supply chain challenges in developing countries and their leading factors. This framework is derived from ISM analysis using a reachability matrix.
{"title":"Supply chain challenges in developing countries: Cross industry case studies","authors":"N. Khalifa, Anthony S. White, A. Elsayed","doi":"10.1109/UKRICIS.2008.4798929","DOIUrl":"https://doi.org/10.1109/UKRICIS.2008.4798929","url":null,"abstract":"Leading firms face various challenges to increase their productivity, reduce costs and improve product quality while improving their profitability. That's why full-package producer have placed each operation in the most cost-effective location. Developing countries have played important role in that. Leading firms have been tempted to locate their manufacturing unit in the developing countries. Competitive material prices and reduced labour costs are main factors, which enable low-income developing countries to enter these global supply chains. This highlights the importance of production capabilities and resource that should be available in these countries. The main objective of this paper is to investigate the challenges that face implementing successful supply chains in these countries. The paper has investigated case studies from different industries to highlight on the common factors that lead to current supply chain deficiencies. As conclusion, the paper proposed a framework indicates supply chain challenges in developing countries and their leading factors. This framework is derived from ISM analysis using a reachability matrix.","PeriodicalId":311925,"journal":{"name":"2008 7th IEEE International Conference on Cybernetic Intelligent Systems","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129183694","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 : 2008-09-01DOI: 10.1109/UKRICIS.2008.4798948
W. Pietruszkiewicz
In this paper we present an application for the dynamical systems and nonlinear filtering in classification. Described here method constitutes a new proposal for the classification of dynamical objects. This method does not require the expansion of dimensionality of the input vectors used in time series, compared to other methods which multiply inputs. The proposed classifier uses the dynamical systems as its core and nonlinear Kalman filtering as its learning algorithm. Presented herein results are the performance tests of proposed classifier applied in a real life problem - bankruptcy prediction, which is one of the fundamentals application of data mining in finance. The results achieved by the presented method were compared to other very popular classifiers and these experiments prove greater classification accuracy of the proposed method.
{"title":"Dynamical systems and nonlinear Kalman filtering applied in classification","authors":"W. Pietruszkiewicz","doi":"10.1109/UKRICIS.2008.4798948","DOIUrl":"https://doi.org/10.1109/UKRICIS.2008.4798948","url":null,"abstract":"In this paper we present an application for the dynamical systems and nonlinear filtering in classification. Described here method constitutes a new proposal for the classification of dynamical objects. This method does not require the expansion of dimensionality of the input vectors used in time series, compared to other methods which multiply inputs. The proposed classifier uses the dynamical systems as its core and nonlinear Kalman filtering as its learning algorithm. Presented herein results are the performance tests of proposed classifier applied in a real life problem - bankruptcy prediction, which is one of the fundamentals application of data mining in finance. The results achieved by the presented method were compared to other very popular classifiers and these experiments prove greater classification accuracy of the proposed method.","PeriodicalId":311925,"journal":{"name":"2008 7th IEEE International Conference on Cybernetic Intelligent Systems","volume":"963 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132480857","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 : 2008-09-01DOI: 10.1109/UKRICIS.2008.4798945
T. Orton, G. Cao, M. Oussalah
The significant increase in memory technology which provided a substantial boost to the capacity made available to the users as well as the emergence of digital and media technology created important challenges to information processing community as the search for efficient and effective digital image within the range of databases becomes a difficult task. This paper investigates the issue of image retrieval system in the light of LIRE open source system and put forward new formalism for combining text and image attributes. Typically, the image attributes consist of MPEG-7 visual descriptors scalar color, color layour, edge histogram and correlogram while the text attribute conveys the various annotations made by the user to describe the content of the image. Lucene text retrieval was used as a basis to integrate the text component. A similarity measure which reinforces the overlapping outcome among various attributes is put forward. Feasibility and evaluation of the proposal are investigated.
{"title":"Personalized content based image retrieval","authors":"T. Orton, G. Cao, M. Oussalah","doi":"10.1109/UKRICIS.2008.4798945","DOIUrl":"https://doi.org/10.1109/UKRICIS.2008.4798945","url":null,"abstract":"The significant increase in memory technology which provided a substantial boost to the capacity made available to the users as well as the emergence of digital and media technology created important challenges to information processing community as the search for efficient and effective digital image within the range of databases becomes a difficult task. This paper investigates the issue of image retrieval system in the light of LIRE open source system and put forward new formalism for combining text and image attributes. Typically, the image attributes consist of MPEG-7 visual descriptors scalar color, color layour, edge histogram and correlogram while the text attribute conveys the various annotations made by the user to describe the content of the image. Lucene text retrieval was used as a basis to integrate the text component. A similarity measure which reinforces the overlapping outcome among various attributes is put forward. Feasibility and evaluation of the proposal are investigated.","PeriodicalId":311925,"journal":{"name":"2008 7th IEEE International Conference on Cybernetic Intelligent Systems","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134397081","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 : 2008-09-01DOI: 10.1109/UKRICIS.2008.4798928
E. Kaldis, Liping Zhao, R. Snowdon
This project aims at recording the knowledge derived from the strategic process of designing the organization. To do this, a framework is proposed in order to capture the changing organizational architecture and acquire strategic knowledge. A software prototype is designed to support the proposed framework. The recording of organizational architecture and organizational intelligence adds a new perspective when developing enterprise information systems.
{"title":"Strategic knowledge representation for the modular organization","authors":"E. Kaldis, Liping Zhao, R. Snowdon","doi":"10.1109/UKRICIS.2008.4798928","DOIUrl":"https://doi.org/10.1109/UKRICIS.2008.4798928","url":null,"abstract":"This project aims at recording the knowledge derived from the strategic process of designing the organization. To do this, a framework is proposed in order to capture the changing organizational architecture and acquire strategic knowledge. A software prototype is designed to support the proposed framework. The recording of organizational architecture and organizational intelligence adds a new perspective when developing enterprise information systems.","PeriodicalId":311925,"journal":{"name":"2008 7th IEEE International Conference on Cybernetic Intelligent Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115452192","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 : 2008-09-01DOI: 10.1109/UKRICIS.2008.4798956
V. Saxena, Sarthak Grover, Sachin Joshi
In this paper, we present a novel real-time face tracking system using rank deficient face detection. Real time computer vision systems need to be fast and efficient to be of practical application. Moreover, the system should be adaptable to diverse real life situations with varied availability of resources. We detect human face in an input grayscale image using a rank deficient face detection algorithm, which has been shown to be 4 to 6 times faster than unconstrained reduced set systems. The algorithm works on grayscale images and so easily adapts to change in ambient conditions like lighting conditions and different people, and is compatible with both color and grayscale cameras. One major problem in face tracking system used in environments with multiple candidate faces is which face to track and how to keep tracking a heuristically selected face without actually involving face authentication procedures. We have developed a highly flexible yet robust algorithm to deal with these problems. In case of multiple faces in the frame, the most prominent face is identified and automatically selected for tracking, and Webcam focused on the desired face. Motion estimation and compensation is then incorporated to ensure robust tracking, to minimize false detections, and for persistent tracking of the desired face. The system showed a robust 10 fps and a false detection rate of 0.6% on a 1.4 GHz Pentium IV workstation using an Intel CS110 Webcam. The principle used in this system can be applied to real time tracking of other objects, viz. cars, the human hand, etc. by using an appropriate training set. It can also be extended to provide face authentication and subsequent tracking of desired face.
{"title":"A real time face tracking system using rank deficient face detection and motion estimation","authors":"V. Saxena, Sarthak Grover, Sachin Joshi","doi":"10.1109/UKRICIS.2008.4798956","DOIUrl":"https://doi.org/10.1109/UKRICIS.2008.4798956","url":null,"abstract":"In this paper, we present a novel real-time face tracking system using rank deficient face detection. Real time computer vision systems need to be fast and efficient to be of practical application. Moreover, the system should be adaptable to diverse real life situations with varied availability of resources. We detect human face in an input grayscale image using a rank deficient face detection algorithm, which has been shown to be 4 to 6 times faster than unconstrained reduced set systems. The algorithm works on grayscale images and so easily adapts to change in ambient conditions like lighting conditions and different people, and is compatible with both color and grayscale cameras. One major problem in face tracking system used in environments with multiple candidate faces is which face to track and how to keep tracking a heuristically selected face without actually involving face authentication procedures. We have developed a highly flexible yet robust algorithm to deal with these problems. In case of multiple faces in the frame, the most prominent face is identified and automatically selected for tracking, and Webcam focused on the desired face. Motion estimation and compensation is then incorporated to ensure robust tracking, to minimize false detections, and for persistent tracking of the desired face. The system showed a robust 10 fps and a false detection rate of 0.6% on a 1.4 GHz Pentium IV workstation using an Intel CS110 Webcam. The principle used in this system can be applied to real time tracking of other objects, viz. cars, the human hand, etc. by using an appropriate training set. It can also be extended to provide face authentication and subsequent tracking of desired face.","PeriodicalId":311925,"journal":{"name":"2008 7th IEEE International Conference on Cybernetic Intelligent Systems","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123581086","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：