Pub Date : 2013-07-10DOI: 10.1109/IISA.2013.6623688
Y. Kokkinos, K. Margaritis
This work describes a probabilistic neural network (PNN) committee machine for Peer-to-Peer data mining. The pattern neurons of the PNN committee are composed of locally trained class-specialized regularization network Peer classifiers. The training takes into account the asynchronous distributed and privacy-preserving requirements that can be met in P2P systems. The Peer classifiers are first trained in parallel based on their local data. While no local data exchange is possible among them, the peers can exchange their classifiers in the form of binaries, or agents. Then an asynchronous distributed computing P2P cycle is executed to construct a mutual validation matrix. The train set of one Peer becomes the validation set of the other and only average rates are returned back. From this matrix we demonstrate that it is possible to perform weight based ensemble selection of best peer members for every class and in this way to find class-specialized Peer modules for the committee machine.
{"title":"Distributed privacy-preserving P2P data mining via probabilistic neural network committee machines","authors":"Y. Kokkinos, K. Margaritis","doi":"10.1109/IISA.2013.6623688","DOIUrl":"https://doi.org/10.1109/IISA.2013.6623688","url":null,"abstract":"This work describes a probabilistic neural network (PNN) committee machine for Peer-to-Peer data mining. The pattern neurons of the PNN committee are composed of locally trained class-specialized regularization network Peer classifiers. The training takes into account the asynchronous distributed and privacy-preserving requirements that can be met in P2P systems. The Peer classifiers are first trained in parallel based on their local data. While no local data exchange is possible among them, the peers can exchange their classifiers in the form of binaries, or agents. Then an asynchronous distributed computing P2P cycle is executed to construct a mutual validation matrix. The train set of one Peer becomes the validation set of the other and only average rates are returned back. From this matrix we demonstrate that it is possible to perform weight based ensemble selection of best peer members for every class and in this way to find class-specialized Peer modules for the committee machine.","PeriodicalId":261368,"journal":{"name":"IISA 2013","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129866417","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 : 2013-07-10DOI: 10.1109/IISA.2013.6623725
A. Benyahia, A. Hajjam, V. Hilaire, M. Hajjam, E. Andrès
In most developed countries; telemonitoring is increasingly used, due to the increasing of life expectancy and chronic diseases that accompany them. Indeed, chronic diseases are responsible for health care costs increasingly growing and remote monitoring systems provide a mean to monitor patients and their needs in the comfort of their own homes, with minimal costs. In older systems, the data were collected and sent directly to the medical experts to be interpreted. With technological advancements, software and systems have been developed for on-site data processing. In this paper, we present E-Care a telemonitoring platform that combines the semantic web and artificial intelligence. E-Care is based on generic ontologies and a decision support system. Ontologies provide knowledge for decision support. The decision support system is based on an inference engine; this engine is used for monitoring the health of the patient and the detection of abnormal situations. System reactions consist in alarms and recommendations for informing physicians. E-Care has a generic open architecture; in this paper we extend the platform by adding a module for auscultation sounds in this architecture.
{"title":"E-Care telemonitoring system: Extend the platform","authors":"A. Benyahia, A. Hajjam, V. Hilaire, M. Hajjam, E. Andrès","doi":"10.1109/IISA.2013.6623725","DOIUrl":"https://doi.org/10.1109/IISA.2013.6623725","url":null,"abstract":"In most developed countries; telemonitoring is increasingly used, due to the increasing of life expectancy and chronic diseases that accompany them. Indeed, chronic diseases are responsible for health care costs increasingly growing and remote monitoring systems provide a mean to monitor patients and their needs in the comfort of their own homes, with minimal costs. In older systems, the data were collected and sent directly to the medical experts to be interpreted. With technological advancements, software and systems have been developed for on-site data processing. In this paper, we present E-Care a telemonitoring platform that combines the semantic web and artificial intelligence. E-Care is based on generic ontologies and a decision support system. Ontologies provide knowledge for decision support. The decision support system is based on an inference engine; this engine is used for monitoring the health of the patient and the detection of abnormal situations. System reactions consist in alarms and recommendations for informing physicians. E-Care has a generic open architecture; in this paper we extend the platform by adding a module for auscultation sounds in this architecture.","PeriodicalId":261368,"journal":{"name":"IISA 2013","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128362406","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 : 2013-07-10DOI: 10.1109/IISA.2013.6623736
S. Sellah, O. Nasraoui
Kernel clustering methods have been used successfully to cluster non linearly separable data. In this paper, we propose a modification of the Kernel K-means, called the Multi-Scale Kernel K-means, that addresses one important challenge, which is the automated estimation of the kernel scale parameters for data containing clusters with different scale values. We propose a novel method that estimates the local kernel scales using the local data density in the original space to learn an adaptive and localized kernel function. Our experimental results with the Multi-Scale Kernel K-means show significant enhancements over the standard Kernel K-means for data sets containing clusters with varying scales and densities.
{"title":"Density-based Kernel Scale estimation for Kernel clustering","authors":"S. Sellah, O. Nasraoui","doi":"10.1109/IISA.2013.6623736","DOIUrl":"https://doi.org/10.1109/IISA.2013.6623736","url":null,"abstract":"Kernel clustering methods have been used successfully to cluster non linearly separable data. In this paper, we propose a modification of the Kernel K-means, called the Multi-Scale Kernel K-means, that addresses one important challenge, which is the automated estimation of the kernel scale parameters for data containing clusters with different scale values. We propose a novel method that estimates the local kernel scales using the local data density in the original space to learn an adaptive and localized kernel function. Our experimental results with the Multi-Scale Kernel K-means show significant enhancements over the standard Kernel K-means for data sets containing clusters with varying scales and densities.","PeriodicalId":261368,"journal":{"name":"IISA 2013","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115587308","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 : 2013-07-10DOI: 10.1109/IISA.2013.6623702
A. Balia, D. Koukopoulos
Nowadays distance learning becomes more and more popular because it is an economical, flexible and self-adaptive form of education. Collaborative learning environments provide users (both learners and instructors) conditions for better communication and cooperation. Moreover, multimedia content due to its friendliness is preferred in such environments as it enhances the learning process. Such environments that are now quite popular can be used for the education in specific cultural areas. Cultural environments are special types of environments where users need the provision of high-quality smart services like collaborative interactive learning applications in a friendly, cheap and personalized way. In this work, we present an online collaborative learning environment where the instructors insert learning material that the learners can view. User and course material classification aims at supporting distance learning scenarios that cover the needs of various user groups such as art classes, teachers and students. This learning material is essentially multimedia cultural content, distributed via the Internet and so it must be protected against any misuse. Therefore, a security scheme is proposed in order to ensure the integrity and the authenticity of the distributed multimedia content. The proposed security scheme is based on attribute-based access control and the usage of digital certificates.
{"title":"A secure collaborative multimedia learning scheme in cultural environments","authors":"A. Balia, D. Koukopoulos","doi":"10.1109/IISA.2013.6623702","DOIUrl":"https://doi.org/10.1109/IISA.2013.6623702","url":null,"abstract":"Nowadays distance learning becomes more and more popular because it is an economical, flexible and self-adaptive form of education. Collaborative learning environments provide users (both learners and instructors) conditions for better communication and cooperation. Moreover, multimedia content due to its friendliness is preferred in such environments as it enhances the learning process. Such environments that are now quite popular can be used for the education in specific cultural areas. Cultural environments are special types of environments where users need the provision of high-quality smart services like collaborative interactive learning applications in a friendly, cheap and personalized way. In this work, we present an online collaborative learning environment where the instructors insert learning material that the learners can view. User and course material classification aims at supporting distance learning scenarios that cover the needs of various user groups such as art classes, teachers and students. This learning material is essentially multimedia cultural content, distributed via the Internet and so it must be protected against any misuse. Therefore, a security scheme is proposed in order to ensure the integrity and the authenticity of the distributed multimedia content. The proposed security scheme is based on attribute-based access control and the usage of digital certificates.","PeriodicalId":261368,"journal":{"name":"IISA 2013","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124473003","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 : 2013-07-10DOI: 10.1109/IISA.2013.6623694
Nicholas Zaranis
The aim of this study is to investigate the question: “Can Information and Communications Technology (ICT) helps to improve primary school students' geometry achievements for rectangles?” The applied educational software consisted of a story and several activities with and without the use of computers which were designed following the background of Realistic Mathematics Education for geometry concepts; referred to as the `Primary Shape Model' (PSM). In addition, we use a mathematical test referred to as the `Primary Shape Test' (PST) to explore the use of ICT in the primary classroom for teaching basic geometrical concepts. It is a task orientated test which attends to measure the level of geometry competence developed for students of the first grade. The study dealt with students in the first grade of primary school of Athens and Crete, who were divided into two teams (experimental and control). The experimental group consisted of 113 students, who were taught of rectangles by the support of computers. There were 121 students in the control group, which received only the traditional science instruction for rectangles. Students in both groups were pre-tested and post-tested for their geometry performance for rectangles. The results of the study indicated that teaching and learning through ICT is an interactive process for children at primary school level and has a positive effect for geometry education of rectangles.
{"title":"The use of Information and Communication Technologies in the first grade of primary school for teaching rectangles based in Realistic Mathematics Education","authors":"Nicholas Zaranis","doi":"10.1109/IISA.2013.6623694","DOIUrl":"https://doi.org/10.1109/IISA.2013.6623694","url":null,"abstract":"The aim of this study is to investigate the question: “Can Information and Communications Technology (ICT) helps to improve primary school students' geometry achievements for rectangles?” The applied educational software consisted of a story and several activities with and without the use of computers which were designed following the background of Realistic Mathematics Education for geometry concepts; referred to as the `Primary Shape Model' (PSM). In addition, we use a mathematical test referred to as the `Primary Shape Test' (PST) to explore the use of ICT in the primary classroom for teaching basic geometrical concepts. It is a task orientated test which attends to measure the level of geometry competence developed for students of the first grade. The study dealt with students in the first grade of primary school of Athens and Crete, who were divided into two teams (experimental and control). The experimental group consisted of 113 students, who were taught of rectangles by the support of computers. There were 121 students in the control group, which received only the traditional science instruction for rectangles. Students in both groups were pre-tested and post-tested for their geometry performance for rectangles. The results of the study indicated that teaching and learning through ICT is an interactive process for children at primary school level and has a positive effect for geometry education of rectangles.","PeriodicalId":261368,"journal":{"name":"IISA 2013","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121166029","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 : 2013-07-10DOI: 10.1109/IISA.2013.6623701
S. Othman, H. Alzaid, A. Trad, H. Youssef
Wireless sensor networks (WSNs) often consists of a large number of low-cost sensor nodes that have strictly limited sensing, computation, and communication capabilities. Due to these unique specifications and a lack of tamper-resistant hardware, devising security protocols for WSNs is complex. Previous studies show that data transmission consumes much more energy than computation. Data aggregation can greatly help to reduce this consumption by eliminating redundant data. As wireless sensor networks are usually deployed in remote and hostile environments and used to transmit sensitive information, sensor nodes are prone to node compromise attacks and hence security issues such as data confidentiality and integrity are extremely important. A novel approach, which uses homomorphic encryption and additive digital signatures, is proposed to provide confidentiality, integrity for secure data aggregation in WSNs. The performance evaluation shows that the proposed scheme is efficient and scalable for large WSNs.
{"title":"An efficient secure data aggregation scheme for wireless sensor networks","authors":"S. Othman, H. Alzaid, A. Trad, H. Youssef","doi":"10.1109/IISA.2013.6623701","DOIUrl":"https://doi.org/10.1109/IISA.2013.6623701","url":null,"abstract":"Wireless sensor networks (WSNs) often consists of a large number of low-cost sensor nodes that have strictly limited sensing, computation, and communication capabilities. Due to these unique specifications and a lack of tamper-resistant hardware, devising security protocols for WSNs is complex. Previous studies show that data transmission consumes much more energy than computation. Data aggregation can greatly help to reduce this consumption by eliminating redundant data. As wireless sensor networks are usually deployed in remote and hostile environments and used to transmit sensitive information, sensor nodes are prone to node compromise attacks and hence security issues such as data confidentiality and integrity are extremely important. A novel approach, which uses homomorphic encryption and additive digital signatures, is proposed to provide confidentiality, integrity for secure data aggregation in WSNs. The performance evaluation shows that the proposed scheme is efficient and scalable for large WSNs.","PeriodicalId":261368,"journal":{"name":"IISA 2013","volume":"285 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122969683","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 : 2013-07-10DOI: 10.1109/IISA.2013.6623716
Mersini Paschou, E. Sakkopoulos, A. Tsakalidis
In this work, we describe an integrated system, developed for use by the healthcare personnel within healthcare facilities, adapted to smartphones, tablets and handheld devices. Our key goal is to facilitate doctors, nurses and the involved personnel throughout the facility, regardless of the existence of network connection in the area using a typical smartphone. The proposed application and its backend system support access to patient's history, i.e. previous diagnoses, medication, and specification of allergies. More features include updates on the progress of the patient, sending referrals directly to hematology, microbiology or biochemistry laboratory and instant notification for the retrieval of laboratory results within a hospital or any healthcare institution. Additionally, we integrate Quick Response (QR code) for coding and accessing medical related data of the patient using a smartphone or a tablet, to be used by the facility itself or anyone else certified. The QR code significantly improves interoperability cases for legacy and non interrelated systems based on HL7 and XML transformation of the HL7 patient referrals.
{"title":"APPification of hospital healthcare and data management using QRcodes","authors":"Mersini Paschou, E. Sakkopoulos, A. Tsakalidis","doi":"10.1109/IISA.2013.6623716","DOIUrl":"https://doi.org/10.1109/IISA.2013.6623716","url":null,"abstract":"In this work, we describe an integrated system, developed for use by the healthcare personnel within healthcare facilities, adapted to smartphones, tablets and handheld devices. Our key goal is to facilitate doctors, nurses and the involved personnel throughout the facility, regardless of the existence of network connection in the area using a typical smartphone. The proposed application and its backend system support access to patient's history, i.e. previous diagnoses, medication, and specification of allergies. More features include updates on the progress of the patient, sending referrals directly to hematology, microbiology or biochemistry laboratory and instant notification for the retrieval of laboratory results within a hospital or any healthcare institution. Additionally, we integrate Quick Response (QR code) for coding and accessing medical related data of the patient using a smartphone or a tablet, to be used by the facility itself or anyone else certified. The QR code significantly improves interoperability cases for legacy and non interrelated systems based on HL7 and XML transformation of the HL7 patient referrals.","PeriodicalId":261368,"journal":{"name":"IISA 2013","volume":"06 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127231974","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 : 2013-07-10DOI: 10.1109/IISA.2013.6623707
Dimitrios Moustis, P. Kotzanikolaou
Distributed Denial of Service attacks generally require a botmaster controlling a large number of infected systems (bots) in order to take down a target service. However, more recent DDoS attacks targeting at the HTTP layer can be very effective even with a small number of infected bots. In this paper we analyze DDoS attacks which require only a small number of bots to render a web server unavailable. In order to study their behavior, we implement a Botnet system in a test environment. We simulate bots by using both Linux and Windows-based systems infected with Slowloris, an HTTP syn-flooder, targeting to a vulnerable Apache web server. We apply several security controls in order to test their effectiveness against such attacks. Our results show that only a combination of carefully selected anti-DDoS controls can significantly reduce the exposure to such attacks without affecting the provided service.
{"title":"Evaluating security controls against HTTP-based DDoS attacks","authors":"Dimitrios Moustis, P. Kotzanikolaou","doi":"10.1109/IISA.2013.6623707","DOIUrl":"https://doi.org/10.1109/IISA.2013.6623707","url":null,"abstract":"Distributed Denial of Service attacks generally require a botmaster controlling a large number of infected systems (bots) in order to take down a target service. However, more recent DDoS attacks targeting at the HTTP layer can be very effective even with a small number of infected bots. In this paper we analyze DDoS attacks which require only a small number of bots to render a web server unavailable. In order to study their behavior, we implement a Botnet system in a test environment. We simulate bots by using both Linux and Windows-based systems infected with Slowloris, an HTTP syn-flooder, targeting to a vulnerable Apache web server. We apply several security controls in order to test their effectiveness against such attacks. Our results show that only a combination of carefully selected anti-DDoS controls can significantly reduce the exposure to such attacks without affecting the provided service.","PeriodicalId":261368,"journal":{"name":"IISA 2013","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127344854","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 : 2013-07-10DOI: 10.1109/IISA.2013.6623720
Panagiota Vatsolaki, A. Tsalpatouros
Electricity Transmission System Interconnectors are critical infrastructures at a national and European level, connecting different electricity areas. Phenomena of capacity demand congestion of the Transmission Interconnectors are handled with auction mechanisms. In this paper, we describe EWOS, a “sealed-bid, first price” method and auction system for electricity auctions. EWOS guarantees the auction security by implementing a transparent and verifiable by all process, based on public-key encryption and a two-phase time protocol. Additional and demanding critical system security and dependability properties are ensured with the use of security policy, and software assurance. EWOS method being secure, reliable and efficient, is used since 2006 for the conduct of numerous daily, monthly and yearly auctions for Transmission Interconnection capacity allocation.
{"title":"EWOS: A sealed-bid auction system design and implementation for electricity interonnector capacity allocation","authors":"Panagiota Vatsolaki, A. Tsalpatouros","doi":"10.1109/IISA.2013.6623720","DOIUrl":"https://doi.org/10.1109/IISA.2013.6623720","url":null,"abstract":"Electricity Transmission System Interconnectors are critical infrastructures at a national and European level, connecting different electricity areas. Phenomena of capacity demand congestion of the Transmission Interconnectors are handled with auction mechanisms. In this paper, we describe EWOS, a “sealed-bid, first price” method and auction system for electricity auctions. EWOS guarantees the auction security by implementing a transparent and verifiable by all process, based on public-key encryption and a two-phase time protocol. Additional and demanding critical system security and dependability properties are ensured with the use of security policy, and software assurance. EWOS method being secure, reliable and efficient, is used since 2006 for the conduct of numerous daily, monthly and yearly auctions for Transmission Interconnection capacity allocation.","PeriodicalId":261368,"journal":{"name":"IISA 2013","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134465987","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 : 2013-07-10DOI: 10.1109/IISA.2013.6623733
A. Tsitsoulis, N. Bourbakis
Extraction of the human body in single, unconstrained, monocular images is a very difficult task. Localization and extraction of the body region, however, provides important and useful knowledge that can facilitate many other tasks, such as gesture recognition, pose estimation and action recognition. In this paper we present a simple appearance-based methodology that combines face detection, skin detection, image segmentation and anthropometric constraints to efficiently estimate the position and regions of hands in images. It requires no training neither explicit estimation of the human pose. Experimental results in a difficult dataset illustrate the performance of the approach.
{"title":"Automatic extraction of upper human body in single images","authors":"A. Tsitsoulis, N. Bourbakis","doi":"10.1109/IISA.2013.6623733","DOIUrl":"https://doi.org/10.1109/IISA.2013.6623733","url":null,"abstract":"Extraction of the human body in single, unconstrained, monocular images is a very difficult task. Localization and extraction of the body region, however, provides important and useful knowledge that can facilitate many other tasks, such as gesture recognition, pose estimation and action recognition. In this paper we present a simple appearance-based methodology that combines face detection, skin detection, image segmentation and anthropometric constraints to efficiently estimate the position and regions of hands in images. It requires no training neither explicit estimation of the human pose. Experimental results in a difficult dataset illustrate the performance of the approach.","PeriodicalId":261368,"journal":{"name":"IISA 2013","volume":"79 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132948179","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：