We present a bionic auditory system for musical instrument recognition. This system is designed based on the physiological structures of the human auditory system that are essential to sound source recognition, such as the basilar membrane and inner hair cells in the cochlea of the inner ear, cochlear nucleus, and the auditory cortex. A large solo database consisting of 243 acoustic and synthetic solo tones over the full pitch ranges of seven different instruments (guitar, harp, horn, piano, saxophone, trumpet, and violin) is used to encompass different sound possibilities of each instrument. The gamma tone model, the Meddis model, and poster ventral cochlear nucleus (PVCN) model are constructed to imitate the basilar membrane, the inner hair cells, and the cochlear nucleus, respectively. By using 33%/67% splits between training and test data, a self-organizing mapping neural network (SOMNN) based on the function of auditory cortex is established to classify the instruments. The instruments are recognized with an overall success rate of over 75%. This bionic auditory system indicates high efficiency and high accuracy in musical instrument recognition.
{"title":"Musical Instrument Recognition Based on the Bionic Auditory Model","authors":"Lin Zhang, Shan Wang, Lianming Wang, Yiyuan Zhang","doi":"10.1109/ISCC-C.2013.91","DOIUrl":"https://doi.org/10.1109/ISCC-C.2013.91","url":null,"abstract":"We present a bionic auditory system for musical instrument recognition. This system is designed based on the physiological structures of the human auditory system that are essential to sound source recognition, such as the basilar membrane and inner hair cells in the cochlea of the inner ear, cochlear nucleus, and the auditory cortex. A large solo database consisting of 243 acoustic and synthetic solo tones over the full pitch ranges of seven different instruments (guitar, harp, horn, piano, saxophone, trumpet, and violin) is used to encompass different sound possibilities of each instrument. The gamma tone model, the Meddis model, and poster ventral cochlear nucleus (PVCN) model are constructed to imitate the basilar membrane, the inner hair cells, and the cochlear nucleus, respectively. By using 33%/67% splits between training and test data, a self-organizing mapping neural network (SOMNN) based on the function of auditory cortex is established to classify the instruments. The instruments are recognized with an overall success rate of over 75%. This bionic auditory system indicates high efficiency and high accuracy in musical instrument recognition.","PeriodicalId":313511,"journal":{"name":"2013 International Conference on Information Science and Cloud Computing Companion","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122349054","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}
In order to improve the overall throughput of processors, to increase thread-level parallelism (TLP) and instruction-level parallelism (ILP) intra and inter cores, and ensure the scalability of multi-core systems, can a novel mechanism chip multithreading with resource unit manager (RUM-CMT) be used, which is presented in this paper. By introducing the efficiency difference of resource utilization among threads, such as, the condition of dynamically resource allocation to CMT architecture and add an absorption barrier for all threads to make their reserved resources far away from hidden hunger. For verify the applicability of RUM-CMT, a 4 cores with 2 threads processor and a 4 cores with 4 threads processor are simulated based on GEMS & Simics simulator. And this limited study shows RUM-CMT can increase performance by 29.79%, and an improve success committed instructions per squash instructions by 31.15% and fairness attains 6.25% improvements over static partition on 4 cores with 4 threads processor. The 4 cores with 2 threads also attains passable enhance. So RUM-CMT can accurately and concise reallocate resource according to phase turning in the running of applications, improve resource utilization, mining the ILP and TLP in applications. In other words, RUM-CMT improves the controllability of threads, reduces invalid losses and improves system efficiency, and it is a suitable solution for multicore, multithreaded architecture.
{"title":"A Case of Chip Multithreading Architecture with Resource Unit Manager","authors":"Juan Fang, Zhenxi Pan, Lu Yu, Sitong Liu","doi":"10.1109/ISCC-C.2013.8","DOIUrl":"https://doi.org/10.1109/ISCC-C.2013.8","url":null,"abstract":"In order to improve the overall throughput of processors, to increase thread-level parallelism (TLP) and instruction-level parallelism (ILP) intra and inter cores, and ensure the scalability of multi-core systems, can a novel mechanism chip multithreading with resource unit manager (RUM-CMT) be used, which is presented in this paper. By introducing the efficiency difference of resource utilization among threads, such as, the condition of dynamically resource allocation to CMT architecture and add an absorption barrier for all threads to make their reserved resources far away from hidden hunger. For verify the applicability of RUM-CMT, a 4 cores with 2 threads processor and a 4 cores with 4 threads processor are simulated based on GEMS & Simics simulator. And this limited study shows RUM-CMT can increase performance by 29.79%, and an improve success committed instructions per squash instructions by 31.15% and fairness attains 6.25% improvements over static partition on 4 cores with 4 threads processor. The 4 cores with 2 threads also attains passable enhance. So RUM-CMT can accurately and concise reallocate resource according to phase turning in the running of applications, improve resource utilization, mining the ILP and TLP in applications. In other words, RUM-CMT improves the controllability of threads, reduces invalid losses and improves system efficiency, and it is a suitable solution for multicore, multithreaded architecture.","PeriodicalId":313511,"journal":{"name":"2013 International Conference on Information Science and Cloud Computing Companion","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126086195","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}
Internet bots are software agents which perform automated tasks. Recently, Twitter bots have become popular and are widely used. However, in order to reduce the load on the Twitter server, one can only make a limited number of connections to the server. You therefore have to design a Twitter bot considering the total number of connections. Model Checking is a technique for verifying automatically whether a model satisfies a given specification. A number of model checkers have been developed, such as SPIN and UPPAAL. In this paper, we study how to apply model checking to analysis of load provided by a bot on the Twitter server. We give a model of a Twitter bot for the UPPAAL model checker. The bot is actually implemented on the Google App Engine. We analyze the dynamic features of the model with respect to restriction of communication with the Twitter server, using the UPPAAL model checker. Finally, we discuss the future direction of our work.
{"title":"Software Analysis of Internet Bots Using a Model Checker","authors":"Eri Koike, S. Nishizaki","doi":"10.1109/ISCC-C.2013.124","DOIUrl":"https://doi.org/10.1109/ISCC-C.2013.124","url":null,"abstract":"Internet bots are software agents which perform automated tasks. Recently, Twitter bots have become popular and are widely used. However, in order to reduce the load on the Twitter server, one can only make a limited number of connections to the server. You therefore have to design a Twitter bot considering the total number of connections. Model Checking is a technique for verifying automatically whether a model satisfies a given specification. A number of model checkers have been developed, such as SPIN and UPPAAL. In this paper, we study how to apply model checking to analysis of load provided by a bot on the Twitter server. We give a model of a Twitter bot for the UPPAAL model checker. The bot is actually implemented on the Google App Engine. We analyze the dynamic features of the model with respect to restriction of communication with the Twitter server, using the UPPAAL model checker. Finally, we discuss the future direction of our work.","PeriodicalId":313511,"journal":{"name":"2013 International Conference on Information Science and Cloud Computing Companion","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128758789","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}
In order to find out the key factors affecting the Information Technology (IT) absorptive capability of Small and Medium-sized Enterprises (SMEs), an empirical study is conducted in this paper. Based on the three-dimensional structure and the influence model of IT absorptive capability proposed by Cuiling Yu, and combined with the characteristics of SMEs, this paper proposes a new model of influence factors, and meanwhile makes an empirical study on the SMEs in Jilin province. Empirical results show that IT consulting, IT infrastructure and government support have significantly impacts on the three-dimension of SMEs' IT absorptive capability. On one hand, the paper reveals how the regions and industries as control variables influence the IT absorptive capacity of SMEs, on the other hand, the paper reveals that IT consulting has a special effect on IT absorptive capacity of SMEs.
{"title":"Factors Affecting Small and Medium-Sized Enterprise's Information Technology Absorptive Capability: An Empirical Study of Jilin Province in China","authors":"Lei Wang, Xinhua Bi, Yue Cao, Meiling Gu","doi":"10.1109/ISCC-C.2013.72","DOIUrl":"https://doi.org/10.1109/ISCC-C.2013.72","url":null,"abstract":"In order to find out the key factors affecting the Information Technology (IT) absorptive capability of Small and Medium-sized Enterprises (SMEs), an empirical study is conducted in this paper. Based on the three-dimensional structure and the influence model of IT absorptive capability proposed by Cuiling Yu, and combined with the characteristics of SMEs, this paper proposes a new model of influence factors, and meanwhile makes an empirical study on the SMEs in Jilin province. Empirical results show that IT consulting, IT infrastructure and government support have significantly impacts on the three-dimension of SMEs' IT absorptive capability. On one hand, the paper reveals how the regions and industries as control variables influence the IT absorptive capacity of SMEs, on the other hand, the paper reveals that IT consulting has a special effect on IT absorptive capacity of SMEs.","PeriodicalId":313511,"journal":{"name":"2013 International Conference on Information Science and Cloud Computing Companion","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133647311","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}
Particle filter algorithm is to achieve recursive Bayesian filter through the simulation method of non-parameter Monte Carlo, It based on sequential importance sampling, and can not avoid particle degeneration problem, a way to overcome the particle degradation is re-sampling, However sample impoverishment will appear in the process of re-sampling, This paper proposes an improved particle filter method based on optimized weight. To some extent, the method solves the particle impoverishment problem, According to simulation results, we can confirm that the improved particle filter algorithm proposed in the paper can effectively improve the estimation precision of particle filter algorithm.
{"title":"The Improved Particle Filter Algorithm Based on Weight Optimization","authors":"Juntao Zhu, Xiaolong Wang, Qiansheng Fang","doi":"10.1109/ISCC-C.2013.140","DOIUrl":"https://doi.org/10.1109/ISCC-C.2013.140","url":null,"abstract":"Particle filter algorithm is to achieve recursive Bayesian filter through the simulation method of non-parameter Monte Carlo, It based on sequential importance sampling, and can not avoid particle degeneration problem, a way to overcome the particle degradation is re-sampling, However sample impoverishment will appear in the process of re-sampling, This paper proposes an improved particle filter method based on optimized weight. To some extent, the method solves the particle impoverishment problem, According to simulation results, we can confirm that the improved particle filter algorithm proposed in the paper can effectively improve the estimation precision of particle filter algorithm.","PeriodicalId":313511,"journal":{"name":"2013 International Conference on Information Science and Cloud Computing Companion","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116687867","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}
Cyber Physical Systems are an emerging discipline that integrates computation and physical processes. With the computation field developed maturely, the major challenges of the implementation of CPSs are the informational abstraction of physical processes and the feedback control on physical processes. The aim of this paper is to provide a description methodology of the physical entity control part, which we named CPSs Hyper Control Mark up Language (CPSsHCML). Through the analysis of TV control part, which is an important physical entity in smart home which is a typical CPSs, the classification of CPSs Hyper Control is obtained in the following four aspects: Function Switch (FS), Discrete Enumerative (DE), Continuous Interval (CI) and Angle Direction (AD). Our work focuses on the definition and description of the attribute fields of global properties and the four CPSs Hyper Controls. In addition, an application of CPSsHCML, which we mentioned above, Sony KLV-40F300A TV in smart home, is provided to show that the prospects of CPSsHCML are promising. Furthermore, some important research challenges and suggestions in future are outlined in brief.
{"title":"A New Model Language for Cyber Physical Systems","authors":"Mingxing Liu, Wubin Ma, Dengsu, Hongbing Huang","doi":"10.1109/ISCC-C.2013.27","DOIUrl":"https://doi.org/10.1109/ISCC-C.2013.27","url":null,"abstract":"Cyber Physical Systems are an emerging discipline that integrates computation and physical processes. With the computation field developed maturely, the major challenges of the implementation of CPSs are the informational abstraction of physical processes and the feedback control on physical processes. The aim of this paper is to provide a description methodology of the physical entity control part, which we named CPSs Hyper Control Mark up Language (CPSsHCML). Through the analysis of TV control part, which is an important physical entity in smart home which is a typical CPSs, the classification of CPSs Hyper Control is obtained in the following four aspects: Function Switch (FS), Discrete Enumerative (DE), Continuous Interval (CI) and Angle Direction (AD). Our work focuses on the definition and description of the attribute fields of global properties and the four CPSs Hyper Controls. In addition, an application of CPSsHCML, which we mentioned above, Sony KLV-40F300A TV in smart home, is provided to show that the prospects of CPSsHCML are promising. Furthermore, some important research challenges and suggestions in future are outlined in brief.","PeriodicalId":313511,"journal":{"name":"2013 International Conference on Information Science and Cloud Computing Companion","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116788025","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}
In the big data era, detecting unsupervised communities in a given dataset, analyzing the evolution of the unsupervised communities, tracing the interests of users are very important. For instance, we can capture user's interest and provide personalized information. In order to detect unsupervised communities in social tagging networks, this paper uses similarity cloud properties of cloud model to solve the different community analysis, classification, and describe the evolutions of unsupervised communities quantitatively and users' dynamic interests in unsupervised communities problems. Cloud model is used in this paper. By introducing similarity cloud properties of cloud model, cloud model can detect the unsupervised communities, describe the evolutions of unsupervised communities quantitatively, and users' dynamic interests in unsupervised communities. For illustration, the proposed model is applied to Delicious dataset to detect unsupervised communities and one month is used as time slice to study the evolutions of the unsupervised communities. Empirical results show that the unsupervised community in social tagging in network, using Similarity cloud properties of cloud model can effectively detect different unsupervised communities, and describe the evolutions of unsupervised communities quantitatively. Similarity cloud properties based cloud model can effectively detect unsupervised community in social tagging network, and quantitatively describe the evolutions of the community and community user' dynamic interest. Hence, CBUCD model is an efficient solution for detecting unsupervised community and analyzing evolutions.
{"title":"Cloud Model: Detect Unsupervised Communities in Social Tagging Networks","authors":"H. Gao, Jing Jiang, Li Zhang, Li Yuchao, Deyi Li","doi":"10.1109/ISCC-C.2013.56","DOIUrl":"https://doi.org/10.1109/ISCC-C.2013.56","url":null,"abstract":"In the big data era, detecting unsupervised communities in a given dataset, analyzing the evolution of the unsupervised communities, tracing the interests of users are very important. For instance, we can capture user's interest and provide personalized information. In order to detect unsupervised communities in social tagging networks, this paper uses similarity cloud properties of cloud model to solve the different community analysis, classification, and describe the evolutions of unsupervised communities quantitatively and users' dynamic interests in unsupervised communities problems. Cloud model is used in this paper. By introducing similarity cloud properties of cloud model, cloud model can detect the unsupervised communities, describe the evolutions of unsupervised communities quantitatively, and users' dynamic interests in unsupervised communities. For illustration, the proposed model is applied to Delicious dataset to detect unsupervised communities and one month is used as time slice to study the evolutions of the unsupervised communities. Empirical results show that the unsupervised community in social tagging in network, using Similarity cloud properties of cloud model can effectively detect different unsupervised communities, and describe the evolutions of unsupervised communities quantitatively. Similarity cloud properties based cloud model can effectively detect unsupervised community in social tagging network, and quantitatively describe the evolutions of the community and community user' dynamic interest. Hence, CBUCD model is an efficient solution for detecting unsupervised community and analyzing evolutions.","PeriodicalId":313511,"journal":{"name":"2013 International Conference on Information Science and Cloud Computing Companion","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134365790","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}
Watching Same Content on Three-Screen TV Continuously (WSC3STVC) has been considered as one of the representative services in smart homes recently. This service offers content mobility among multiple kinds of screens based on user position in home. Quality of Experience (QoE) and service implementation cost are two important challenges for supporting WSC3STVC service. To the best of our knowledge, there is no visible attempt to design a comprehensive platform for supporting this service in smart homes. Benefiting from cloud computing, peer-to-peer (P2P) network, clustering and H.264 SVC transcoding, this paper proposes a QoE-aware and cost-effective platform for supporting WSC3STVC service in smart home. The strong points of the proposed platform are transcoding in cloud instead of Home GateWay (HGW) for decreasing HGW cost, content switching inside HGW for reducing service delay, using a cloud-managed P2P network for improving bandwidth between cloud and homes and also clustering homes for reducing transfer delay between homes.
{"title":"A Cloud-Based Platform for Watching Same Content on Three-Screen TV Continuously in Smart Home","authors":"E. Ahvar, G. Lee, N. Crespi","doi":"10.1109/ISCC-C.2013.9","DOIUrl":"https://doi.org/10.1109/ISCC-C.2013.9","url":null,"abstract":"Watching Same Content on Three-Screen TV Continuously (WSC3STVC) has been considered as one of the representative services in smart homes recently. This service offers content mobility among multiple kinds of screens based on user position in home. Quality of Experience (QoE) and service implementation cost are two important challenges for supporting WSC3STVC service. To the best of our knowledge, there is no visible attempt to design a comprehensive platform for supporting this service in smart homes. Benefiting from cloud computing, peer-to-peer (P2P) network, clustering and H.264 SVC transcoding, this paper proposes a QoE-aware and cost-effective platform for supporting WSC3STVC service in smart home. The strong points of the proposed platform are transcoding in cloud instead of Home GateWay (HGW) for decreasing HGW cost, content switching inside HGW for reducing service delay, using a cloud-managed P2P network for improving bandwidth between cloud and homes and also clustering homes for reducing transfer delay between homes.","PeriodicalId":313511,"journal":{"name":"2013 International Conference on Information Science and Cloud Computing Companion","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134441340","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}
In this paper, an anti-phishing technique based on e-mail extraction and analysis is proposed. The technique approached with phishing email, the channel phishing attack transmits, distinguish phishing emails and extract the suspicious URL from the e-mail for further analysis. Upon arrival, a protected list is built according to those third parties which are the most vulnerable to phishers in order to filter those confusing advertising spams in China and a neural network based model is proposed in order to detecting phishing messages from an e-mail stream. In this anti-phishing technique, email stream captured by our honey pot subsystem from the Internet is parsed into a MIME email firstly, various feathers are extracted from the email and outputted into feather vectors. The feature vectors will be self-organized by ART2 neural network one by one and classified into corresponding categories. Link URLs in the suspected emails' messages will be extracted for further detection in phishing site subsystem. Experiment using collected emails shows a good performance aiming at detecting phishing emails in China while foreign method performs badly in distinguishing phishing emails from spam.
{"title":"Research of the Anti-phishing Technology Based on E-mail Extraction and Analysis","authors":"Yanhui Du, Fu Xue","doi":"10.1109/ISCC-C.2013.110","DOIUrl":"https://doi.org/10.1109/ISCC-C.2013.110","url":null,"abstract":"In this paper, an anti-phishing technique based on e-mail extraction and analysis is proposed. The technique approached with phishing email, the channel phishing attack transmits, distinguish phishing emails and extract the suspicious URL from the e-mail for further analysis. Upon arrival, a protected list is built according to those third parties which are the most vulnerable to phishers in order to filter those confusing advertising spams in China and a neural network based model is proposed in order to detecting phishing messages from an e-mail stream. In this anti-phishing technique, email stream captured by our honey pot subsystem from the Internet is parsed into a MIME email firstly, various feathers are extracted from the email and outputted into feather vectors. The feature vectors will be self-organized by ART2 neural network one by one and classified into corresponding categories. Link URLs in the suspected emails' messages will be extracted for further detection in phishing site subsystem. Experiment using collected emails shows a good performance aiming at detecting phishing emails in China while foreign method performs badly in distinguishing phishing emails from spam.","PeriodicalId":313511,"journal":{"name":"2013 International Conference on Information Science and Cloud Computing Companion","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124088739","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}
There have been considerable research efforts to use the hand as an input device for HCI in recent years. Hand tracking is the most important procedure for HCI, it is essential of tracking stability and efficiency for hand manipulation. This paper proposed a novel hand tracking algorithm which can track a hand stable and is real time, and the proposed algorithm can work on normal CCD cameral. Our algorithm is based on mean-shift and we improved it to fit for robust hand tracking by using super pixel cluster, integrated GIH and skin color mask, the skin color mask was extracted using online learning. The proposed improved algorithm can track hand reliably even in clutter environments comparing to the existing traditional algorithms.
{"title":"Hand Tracking Algorithm Based on SuperPixels Feature","authors":"Zhiqin Zhang, Fei Huang","doi":"10.1109/ISCC-C.2013.77","DOIUrl":"https://doi.org/10.1109/ISCC-C.2013.77","url":null,"abstract":"There have been considerable research efforts to use the hand as an input device for HCI in recent years. Hand tracking is the most important procedure for HCI, it is essential of tracking stability and efficiency for hand manipulation. This paper proposed a novel hand tracking algorithm which can track a hand stable and is real time, and the proposed algorithm can work on normal CCD cameral. Our algorithm is based on mean-shift and we improved it to fit for robust hand tracking by using super pixel cluster, integrated GIH and skin color mask, the skin color mask was extracted using online learning. The proposed improved algorithm can track hand reliably even in clutter environments comparing to the existing traditional algorithms.","PeriodicalId":313511,"journal":{"name":"2013 International Conference on Information Science and Cloud Computing Companion","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121055812","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}