Pub Date : 2009-12-28DOI: 10.1109/ICACIA.2009.5361092
Dekun Hu, Jiang-Ping Li, S. Yang, S. Gregori
To segment an object from its background image for advanced vision processing, this article presents a novel bio-inspired framework for image segmentation in complex nature scenes, which is a hierarchical system that mimics the organization of layered early visual area in primate visual cortex. The proposed methodology consists of two typical stages: the first stage is a parallel modular structure including three segmenting operators based on color feature, form feature and texture feature, each of which solves the segmentation problem independently for the same input. They implement the similar computing as the parvocellular (P-cell), the magnocellular (M-cell) and koniocellular (K-cell) pathway in lateral geniculate nucleus (LGN) from the retina to the primary visual cortex. Then, a fusion operation, multiple feature fusion segmentation (MFFS), integrates these three feature segmentations together through the backpropagation neuron network (BPNN) in the last stage, which simulates the operation of area following the LGN in primary visual cortex. The proposed approach is applied to several segmentation experiments of many single objects in clustering conditions, the result shows that the approach is capable of competing with state-of-the-art systems.
{"title":"A bio-inspired model for color image segmentation","authors":"Dekun Hu, Jiang-Ping Li, S. Yang, S. Gregori","doi":"10.1109/ICACIA.2009.5361092","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361092","url":null,"abstract":"To segment an object from its background image for advanced vision processing, this article presents a novel bio-inspired framework for image segmentation in complex nature scenes, which is a hierarchical system that mimics the organization of layered early visual area in primate visual cortex. The proposed methodology consists of two typical stages: the first stage is a parallel modular structure including three segmenting operators based on color feature, form feature and texture feature, each of which solves the segmentation problem independently for the same input. They implement the similar computing as the parvocellular (P-cell), the magnocellular (M-cell) and koniocellular (K-cell) pathway in lateral geniculate nucleus (LGN) from the retina to the primary visual cortex. Then, a fusion operation, multiple feature fusion segmentation (MFFS), integrates these three feature segmentations together through the backpropagation neuron network (BPNN) in the last stage, which simulates the operation of area following the LGN in primary visual cortex. The proposed approach is applied to several segmentation experiments of many single objects in clustering conditions, the result shows that the approach is capable of competing with state-of-the-art systems.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131203419","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 : 2009-12-28DOI: 10.1109/ICACIA.2009.5361090
Yuan-Yuan Huang, Jianping Li, Jie Lin, Yujie Hao, Guiduo Duan
This paper firstly shows the entire picture of a promising research area, face recognition. Then a new face recognition method is proposed, mainly based on the combination of wavelet transform and local hybrid projection entropy (LHPE). Some classical image processing methods are included to constitute a cascade framework. The experimental results on Yale face database and Yale B face database show that this method is effective and competitive, especially robust to illumination changes.
{"title":"Robust face recognition by combining wavelet decomposition and local hybrid projection entropy","authors":"Yuan-Yuan Huang, Jianping Li, Jie Lin, Yujie Hao, Guiduo Duan","doi":"10.1109/ICACIA.2009.5361090","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361090","url":null,"abstract":"This paper firstly shows the entire picture of a promising research area, face recognition. Then a new face recognition method is proposed, mainly based on the combination of wavelet transform and local hybrid projection entropy (LHPE). Some classical image processing methods are included to constitute a cascade framework. The experimental results on Yale face database and Yale B face database show that this method is effective and competitive, especially robust to illumination changes.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125389426","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 : 2009-12-28DOI: 10.1109/ICACIA.2009.5361106
Li Ren, Haipeng He, Zhao Di, Ming Lei
The network communication applying network coding, in which the intermediate peers firstly encode the information from source, and then forward the encoded data which will be decoded by the destination peers where the original information gets restored. Previous methods indicate that we can improve throughput and stability of a network, fasten the expanding-velocity of copies, and reduce the download time. Although network coding technology is developing so fast, the critical issue is still how to promote encoding and decoding rates and to decrease the complexity, on which we focus in the field. In this paper, we propose an approach based on segmented network coding which is applied to P2P Content Distribution System (P2PCDS). We implement a P2PCDS based on segmented network coding. Through the experiment, we choose the number of encoding data as a seed, and make a comparison between the P2PCDS with and without network coding in term of average download time and in the resist of churn. The resist of churn in our system is raised by 12.5 % and it also shortens average download time. And the experiment shows it's better to adapt P2PCDS under the active Mesh network architecture.
{"title":"Content distribution system based on segmented network coding","authors":"Li Ren, Haipeng He, Zhao Di, Ming Lei","doi":"10.1109/ICACIA.2009.5361106","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361106","url":null,"abstract":"The network communication applying network coding, in which the intermediate peers firstly encode the information from source, and then forward the encoded data which will be decoded by the destination peers where the original information gets restored. Previous methods indicate that we can improve throughput and stability of a network, fasten the expanding-velocity of copies, and reduce the download time. Although network coding technology is developing so fast, the critical issue is still how to promote encoding and decoding rates and to decrease the complexity, on which we focus in the field. In this paper, we propose an approach based on segmented network coding which is applied to P2P Content Distribution System (P2PCDS). We implement a P2PCDS based on segmented network coding. Through the experiment, we choose the number of encoding data as a seed, and make a comparison between the P2PCDS with and without network coding in term of average download time and in the resist of churn. The resist of churn in our system is raised by 12.5 % and it also shortens average download time. And the experiment shows it's better to adapt P2PCDS under the active Mesh network architecture.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"176 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124342265","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 : 2009-12-28DOI: 10.1109/ICACIA.2009.5361113
Guo Rongxiang
Elimination method is an effective method for solving non-linear polynomial equations. It mainly includes Wu's methods, Grobner base and resultant methods. Dixon resultant is more efficient than other resultant methods. But Dixon matrix enlarges greatly when the polynomial sets have higher rank. Pro.Fu Hongguang et al worked out the recursive algorithm for computing Dixon resultant polynomial, by which the computation unit can be reduced. In this paper, distributed computing model for Dixon resultant is presented. GiNaC is transplanted and extended into distributed computing environment. The solution to communication etc problems is suggested. The system design and implementation are introduced, the computation result is given.
{"title":"Distributed computation of dixon resultant with changeable arguments","authors":"Guo Rongxiang","doi":"10.1109/ICACIA.2009.5361113","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361113","url":null,"abstract":"Elimination method is an effective method for solving non-linear polynomial equations. It mainly includes Wu's methods, Grobner base and resultant methods. Dixon resultant is more efficient than other resultant methods. But Dixon matrix enlarges greatly when the polynomial sets have higher rank. Pro.Fu Hongguang et al worked out the recursive algorithm for computing Dixon resultant polynomial, by which the computation unit can be reduced. In this paper, distributed computing model for Dixon resultant is presented. GiNaC is transplanted and extended into distributed computing environment. The solution to communication etc problems is suggested. The system design and implementation are introduced, the computation result is given.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116640347","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 : 2009-12-28DOI: 10.1109/ICACIA.2009.5361087
Jin-Xin Shi, Xiaofeng Gu, Jianping Li, Jie Lin, Lin Liu, Yuan-Yuan Huang
At present, the research of biometric recognition is gave more and more attention in the world. The iris recognition is a kind of the biometrics technologies based on the physiological characteristics of human body, compared with the feature recognition based on the fingerprint, palm-print, face and sound etc. the iris recognition technology has recently become popular in identity recognition. In my paper, based on the existing iris location algorithm, an improved iris location algorithm is brought forward. This method can achieve a precise and rapid iris location. In this method, inner circle positioning algorithm is improved by the changed Ostu adaptive binarization thresholding algorithm and the changed gray-scale projection method. And external positioning is completed by Roberts operator.
{"title":"A new method of iris image location research","authors":"Jin-Xin Shi, Xiaofeng Gu, Jianping Li, Jie Lin, Lin Liu, Yuan-Yuan Huang","doi":"10.1109/ICACIA.2009.5361087","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361087","url":null,"abstract":"At present, the research of biometric recognition is gave more and more attention in the world. The iris recognition is a kind of the biometrics technologies based on the physiological characteristics of human body, compared with the feature recognition based on the fingerprint, palm-print, face and sound etc. the iris recognition technology has recently become popular in identity recognition. In my paper, based on the existing iris location algorithm, an improved iris location algorithm is brought forward. This method can achieve a precise and rapid iris location. In this method, inner circle positioning algorithm is improved by the changed Ostu adaptive binarization thresholding algorithm and the changed gray-scale projection method. And external positioning is completed by Roberts operator.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129437092","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 : 2009-12-28DOI: 10.1109/ICACIA.2009.5361076
Jianming Liao, Yu Liu
Worldwide attention has been gained by WirelessHART networks particularly in recent years, which has integrated sensor technology, wireless communication technology and computer technology with the ability of information collection, transmission and processing in low cost and low power consumption. It has several important applications such as remote environment monitoring, asset monitoring and flow measurement. This paper is mainly written to describe, in WirelessHART networks, the design and implementation of a specific application named distributed flowmeter data acquisition system, which is a project cooperated with General Electric Company, with the key technologies in wireless networks, hardware environment and software environment.
{"title":"Distributed flowmeter data acquisition system based on WirelessHART networks","authors":"Jianming Liao, Yu Liu","doi":"10.1109/ICACIA.2009.5361076","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361076","url":null,"abstract":"Worldwide attention has been gained by WirelessHART networks particularly in recent years, which has integrated sensor technology, wireless communication technology and computer technology with the ability of information collection, transmission and processing in low cost and low power consumption. It has several important applications such as remote environment monitoring, asset monitoring and flow measurement. This paper is mainly written to describe, in WirelessHART networks, the design and implementation of a specific application named distributed flowmeter data acquisition system, which is a project cooperated with General Electric Company, with the key technologies in wireless networks, hardware environment and software environment.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127867091","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 : 2009-12-28DOI: 10.1109/ICACIA.2009.5361100
Hu Jian, Liu Xiaobin
Multicast technology introduces a number of new applications; meanwhile, it reduces the congestion of the network and releases the burden of the server. Those characteristics, such as reducing the occupied bandwidth, reducing server load, improving the quality of data transmission, are especially applicable to the needs of large bandwidth multimedia applications such as audio, Video. This new technology has become a hot topic in Internet circles, and to fundamentally change the network architecture. Although multicast technology has also brought some problems, such as routing instability, the network load imbalance, QoS fluctuations, but its application is still very wide.
{"title":"The application in multicast of the P2P routing mechanisms based on the content addressing networks","authors":"Hu Jian, Liu Xiaobin","doi":"10.1109/ICACIA.2009.5361100","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361100","url":null,"abstract":"Multicast technology introduces a number of new applications; meanwhile, it reduces the congestion of the network and releases the burden of the server. Those characteristics, such as reducing the occupied bandwidth, reducing server load, improving the quality of data transmission, are especially applicable to the needs of large bandwidth multimedia applications such as audio, Video. This new technology has become a hot topic in Internet circles, and to fundamentally change the network architecture. Although multicast technology has also brought some problems, such as routing instability, the network load imbalance, QoS fluctuations, but its application is still very wide.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"11 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120900794","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 : 2009-12-28DOI: 10.1109/ICACIA.2009.5361065
Qi Xing-ming, Hua Zhi-gang, Jiao Jin-yi
Based on one boat, the intensity analysis and optimization design of gas turbine install system was presented. Firstly, the theory calculation results of the interactive forces between gas turbine and track system was performed. After then, the 3-D grid paramedical model of track system was established. The detailed information of flow field shows that the intensity of track system meets well with requirements. Meanwhile, the transition part of track system presents the weakest intensity. Consequently, the optimization design of install track system structure was carried out. The total mass of track system dramatically reduced, which meets the intensity standard as well.
{"title":"Optimization design of gas turbine install track system","authors":"Qi Xing-ming, Hua Zhi-gang, Jiao Jin-yi","doi":"10.1109/ICACIA.2009.5361065","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361065","url":null,"abstract":"Based on one boat, the intensity analysis and optimization design of gas turbine install system was presented. Firstly, the theory calculation results of the interactive forces between gas turbine and track system was performed. After then, the 3-D grid paramedical model of track system was established. The detailed information of flow field shows that the intensity of track system meets well with requirements. Meanwhile, the transition part of track system presents the weakest intensity. Consequently, the optimization design of install track system structure was carried out. The total mass of track system dramatically reduced, which meets the intensity standard as well.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"249 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116190107","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 : 2009-12-28DOI: 10.1109/ICACIA.2009.5361147
Zhenye Xu, Chun Yang
Considering the multiplicity mT (λ) of eigenvalue λ (which equals 1) of Laplacian matrix of all trees, we get three results: When mT (1) equals n-2, the tree is unique, that is star graph K1,n-1; (ii) there exists no trees satisfying mT (1) equals n-3; (iii) When mT (1) equals n-4, this kind of trees are divided into two types. According to the process of proving, we devise a method to construct trees on some desired properties, which have practical value.
{"title":"A note on multiplicity of the Laplacian eigenvalue of trees","authors":"Zhenye Xu, Chun Yang","doi":"10.1109/ICACIA.2009.5361147","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361147","url":null,"abstract":"Considering the multiplicity m<inf>T</inf> (λ) of eigenvalue λ (which equals 1) of Laplacian matrix of all trees, we get three results: When m<inf>T</inf> (1) equals n-2, the tree is unique, that is star graph K<inf>1,n-1</inf>; (ii) there exists no trees satisfying m<inf>T</inf> (1) equals n-3; (iii) When m<inf>T</inf> (1) equals n-4, this kind of trees are divided into two types. According to the process of proving, we devise a method to construct trees on some desired properties, which have practical value.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128364123","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 : 2009-12-28DOI: 10.1109/ICACIA.2009.5361060
S. Wang, Shupin Ning
Tension feed-forward control method based on filament deform is presented in terms of filament tension generation theory. Tension control integrated system of six-axis filament winding machine is set up. Through motion analysis to non-geodesic windings for revolution object and control of resin's temperature, the equation of filament tension according to extension length is established, thus improves the control precision of tension in filament composite wound components.
{"title":"Research on tension control for six-axis filament winding machine","authors":"S. Wang, Shupin Ning","doi":"10.1109/ICACIA.2009.5361060","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361060","url":null,"abstract":"Tension feed-forward control method based on filament deform is presented in terms of filament tension generation theory. Tension control integrated system of six-axis filament winding machine is set up. Through motion analysis to non-geodesic windings for revolution object and control of resin's temperature, the equation of filament tension according to extension length is established, thus improves the control precision of tension in filament composite wound components.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126968544","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：