Wang Chun-mei, Wang Su-zhen, Zhang Chong-ming, Zou Jun-zhong
An image segmentation method based on the OTSU and improved genetic algorithm (GA) is presented. The OTSU is taken as evaluation function and the segmentation problem is turned to the optimization problem. That is, GA efficiently searches the segmentation parameter space in order to obtain the optimal threshold. On the other hand, to overcome some limitation of GA, elite reinsertion is applied. The experimental results indicate that the method can not only obtain a better result, but also shorten the processing time.
{"title":"Maximum Variance Image Segmentation Based on Improved Genetic Algorithm","authors":"Wang Chun-mei, Wang Su-zhen, Zhang Chong-ming, Zou Jun-zhong","doi":"10.1109/SNPD.2007.353","DOIUrl":"https://doi.org/10.1109/SNPD.2007.353","url":null,"abstract":"An image segmentation method based on the OTSU and improved genetic algorithm (GA) is presented. The OTSU is taken as evaluation function and the segmentation problem is turned to the optimization problem. That is, GA efficiently searches the segmentation parameter space in order to obtain the optimal threshold. On the other hand, to overcome some limitation of GA, elite reinsertion is applied. The experimental results indicate that the method can not only obtain a better result, but also shorten the processing time.","PeriodicalId":197058,"journal":{"name":"Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121089999","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}
A new improved edge detection algorithm of images based on cellular automata is presented. This method uses direction information measure and edge order measure as edge characteristic information, uses fuzzy logic to inference these information, processes inference results by anti-fuzzy, gives feedback information to direction information measure matrix, and detects edge by automatic evolution of cellular automata. Finally, experiments are put forward, this algorithm has powerful ability in detection fuzzy edge and exiguous edge, and it is a promising and applied image processing algorithm.
{"title":"Edge Detection of Images based on Fuzzy Cellular Automata","authors":"Ke Zhang, Zhong Li, Xiaoou Zhao","doi":"10.1109/SNPD.2007.167","DOIUrl":"https://doi.org/10.1109/SNPD.2007.167","url":null,"abstract":"A new improved edge detection algorithm of images based on cellular automata is presented. This method uses direction information measure and edge order measure as edge characteristic information, uses fuzzy logic to inference these information, processes inference results by anti-fuzzy, gives feedback information to direction information measure matrix, and detects edge by automatic evolution of cellular automata. Finally, experiments are put forward, this algorithm has powerful ability in detection fuzzy edge and exiguous edge, and it is a promising and applied image processing algorithm.","PeriodicalId":197058,"journal":{"name":"Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116050986","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}
Image fusion is the process of combing multiple images of the same scene into a single fused image with the aim of preserving the full content information and retaining the important features from each of the original images. In this paper, we propose a novel scheme to measure every wavelet decomposition coefficient's saliency of the original images. The saliency value reflects the visually meaningful content of the wavelet decomposition coefficients and is consistent with human visual perception. The novel scheme aims to preserve the full content value and retain the visually meaningful information with human visual perception more exactly than the traditional method. In addition, the proposed novel method can be combined with any sophisticated fusion rules and fusion operators that are based on wavelet decomposition. Experimental results show the effectiveness of the proposed scheme, which can retain perceptually important image information.
{"title":"Image Fusion Based on Wavelet Transform","authors":"Muwei Jian, Junyu Dong, Yang Zhang","doi":"10.1109/SNPD.2007.110","DOIUrl":"https://doi.org/10.1109/SNPD.2007.110","url":null,"abstract":"Image fusion is the process of combing multiple images of the same scene into a single fused image with the aim of preserving the full content information and retaining the important features from each of the original images. In this paper, we propose a novel scheme to measure every wavelet decomposition coefficient's saliency of the original images. The saliency value reflects the visually meaningful content of the wavelet decomposition coefficients and is consistent with human visual perception. The novel scheme aims to preserve the full content value and retain the visually meaningful information with human visual perception more exactly than the traditional method. In addition, the proposed novel method can be combined with any sophisticated fusion rules and fusion operators that are based on wavelet decomposition. Experimental results show the effectiveness of the proposed scheme, which can retain perceptually important image information.","PeriodicalId":197058,"journal":{"name":"Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116211532","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}
To study effective speech features which can represent different emotion styles in mandarin speech, nonlinear features based on Teager Energy Operator(TEO) are researched. Neutral state and 3 emotional states (i.e. happiness, anger and sadness) are classified from the mandarin speech database. MFCC extraction and HMM-based emotion recognition are used as baseline system to evaluate the emotional classification performance of TEO-based features. In comparison with MFCC, while text- dependent, improvements of classification capacity are obtained when using all 4 nonlinear features (i.e. NFD_Mel, AF_Mel, DAF_Mel, AM_SBCC). While text-independent, the performance of emotion classification are improved by using NFD_Mel, AF_Mel and DAF_Mel, but deteriorated by using AM_SBCC. The results of classification demonstrate that the nonlinear features based on TEO, when using NFD_Mel, AF_Mel and DAF_Mel, are better able to represent different emotion styles in speech than that of MFCC.
{"title":"Emotion Classification of Mandarin Speech Based on TEO Nonlinear Features","authors":"Gao Hui, Chen Shanguang, Su Guangchuan","doi":"10.1109/SNPD.2007.487","DOIUrl":"https://doi.org/10.1109/SNPD.2007.487","url":null,"abstract":"To study effective speech features which can represent different emotion styles in mandarin speech, nonlinear features based on Teager Energy Operator(TEO) are researched. Neutral state and 3 emotional states (i.e. happiness, anger and sadness) are classified from the mandarin speech database. MFCC extraction and HMM-based emotion recognition are used as baseline system to evaluate the emotional classification performance of TEO-based features. In comparison with MFCC, while text- dependent, improvements of classification capacity are obtained when using all 4 nonlinear features (i.e. NFD_Mel, AF_Mel, DAF_Mel, AM_SBCC). While text-independent, the performance of emotion classification are improved by using NFD_Mel, AF_Mel and DAF_Mel, but deteriorated by using AM_SBCC. The results of classification demonstrate that the nonlinear features based on TEO, when using NFD_Mel, AF_Mel and DAF_Mel, are better able to represent different emotion styles in speech than that of MFCC.","PeriodicalId":197058,"journal":{"name":"Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007)","volume":"293 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123742123","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}
Reducing communication overhead is extremely important for parallelizing compiler to generate efficient codes for distributed memory machines. In this paper, a redundant parallel execution model (RPEM) is used as the model for target programs. The extend data flow graph is introduced, and optimization algorithms based on the data-flow analysis are discussed. The overhead of data flow analysis can be reduced by performing analysis on the extend dataflow graph. The analysis helps to reduce the redundant communication overhead. These optimization algorithms are able to perform inter-loop and inter-procedure analysis. Experimental results prove that these optimizations algorithms are effective in reducing both the number of communications and the communication volume.
{"title":"Communication Optimization Algorithms based on Extend Data Flow Graph","authors":"Xuerong Gong, Linsheng Lu, Rongcai Zhao","doi":"10.1109/SNPD.2007.168","DOIUrl":"https://doi.org/10.1109/SNPD.2007.168","url":null,"abstract":"Reducing communication overhead is extremely important for parallelizing compiler to generate efficient codes for distributed memory machines. In this paper, a redundant parallel execution model (RPEM) is used as the model for target programs. The extend data flow graph is introduced, and optimization algorithms based on the data-flow analysis are discussed. The overhead of data flow analysis can be reduced by performing analysis on the extend dataflow graph. The analysis helps to reduce the redundant communication overhead. These optimization algorithms are able to perform inter-loop and inter-procedure analysis. Experimental results prove that these optimizations algorithms are effective in reducing both the number of communications and the communication volume.","PeriodicalId":197058,"journal":{"name":"Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007)","volume":"38 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114033082","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}
Independent component analysis (ICA) has found its application in face recognition successfully. In practice several ICA representations can be derived. Particularly they include spatial ICA, spatiotemporal ICA, and localized spatiotemporal ICA, which respectively extract features of face images in terms of space domain, time-space domain, and local region. Our work has shown that while spatiotemporal ICA outperforms other ICA representations, further improvement can be made by a fusion of variety of ICA features. However, simply combining all features will not work as well as expected. For this reason an optimization method for feature selection and combination is proposed in this paper. We present here an optimizing process of feature selection about which features and how many features from each individual ICA feature set are selected. The experimental results show that feature fusion method can improve face recognition rate up to 94.62% compared with that of 86.43% by using spatiotemporal ICA alone.
{"title":"Fusion of ICA Spatial, Temporal and Localized Features for Face Recognition","authors":"Jiajin Lei, Chao Lu","doi":"10.1109/SNPD.2007.517","DOIUrl":"https://doi.org/10.1109/SNPD.2007.517","url":null,"abstract":"Independent component analysis (ICA) has found its application in face recognition successfully. In practice several ICA representations can be derived. Particularly they include spatial ICA, spatiotemporal ICA, and localized spatiotemporal ICA, which respectively extract features of face images in terms of space domain, time-space domain, and local region. Our work has shown that while spatiotemporal ICA outperforms other ICA representations, further improvement can be made by a fusion of variety of ICA features. However, simply combining all features will not work as well as expected. For this reason an optimization method for feature selection and combination is proposed in this paper. We present here an optimizing process of feature selection about which features and how many features from each individual ICA feature set are selected. The experimental results show that feature fusion method can improve face recognition rate up to 94.62% compared with that of 86.43% by using spatiotemporal ICA alone.","PeriodicalId":197058,"journal":{"name":"Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125310146","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}
Jianhua Sun, Jizha Qin, Shu Chen, Hao Chen, Dingding Li
With the development of computers and Internet, more and more people use email. Viruses of email have caused large damages. Traditional intentional immunization based on nodes degree does not take the positions of infected nodes into account, and protects the nodes which have high degree. We introduce the concept of community into the research field of virus and immunization, and propose an immunization model based on communities. According to the different stages of virus infection, this model immunizes infected communities or healthy communities, which slows down the virus spreading rate and keeps virus from spreading to more communities. Degree immunization can not keep the virus in a part of communities, and as a result the infected nodes diffuse in almost all communities. Communities immunization can keep the virus in a certain number of communities. These two models are different in the ratio of infected communities and infected communities vector. In summary, communities immunization is different from the degree immunization completely, and is a novel and effective scheme.
{"title":"A Virus Immunization Model Based on Communities in Large Scale Networks","authors":"Jianhua Sun, Jizha Qin, Shu Chen, Hao Chen, Dingding Li","doi":"10.1109/SNPD.2007.501","DOIUrl":"https://doi.org/10.1109/SNPD.2007.501","url":null,"abstract":"With the development of computers and Internet, more and more people use email. Viruses of email have caused large damages. Traditional intentional immunization based on nodes degree does not take the positions of infected nodes into account, and protects the nodes which have high degree. We introduce the concept of community into the research field of virus and immunization, and propose an immunization model based on communities. According to the different stages of virus infection, this model immunizes infected communities or healthy communities, which slows down the virus spreading rate and keeps virus from spreading to more communities. Degree immunization can not keep the virus in a part of communities, and as a result the infected nodes diffuse in almost all communities. Communities immunization can keep the virus in a certain number of communities. These two models are different in the ratio of infected communities and infected communities vector. In summary, communities immunization is different from the degree immunization completely, and is a novel and effective scheme.","PeriodicalId":197058,"journal":{"name":"Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007)","volume":"253 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122660233","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}
Radars are common means to measure vehicle speed. They are fast and accurate, however measure only instantaneous velocity not speed of the traffic flow. Therefore they are not suitable to help determine the busy degree of traffic. A novel method of traffic flow speed measurement using video based on time domain cross correlation is introduced. It provides 'flow speed', a much better parameter determining whether there is a traffic jam or how fast one can cover that road under the observed situation. With regard to the 'False-Peak' problem, effect of the sequence length on correlation result is presented, together with formulas used to calculate proper sequence length both accurately and approximately. Test results demonstrate the signification of sequence length on improving cross correlation result and good accuracy suitable for estimation of road busy degree.
{"title":"Application and Analysis of Time Domain Cross Correlation for Traffic Flow Speed Measurement","authors":"Lichao Wang, Qiyong Lu, X. Chen","doi":"10.1109/SNPD.2007.339","DOIUrl":"https://doi.org/10.1109/SNPD.2007.339","url":null,"abstract":"Radars are common means to measure vehicle speed. They are fast and accurate, however measure only instantaneous velocity not speed of the traffic flow. Therefore they are not suitable to help determine the busy degree of traffic. A novel method of traffic flow speed measurement using video based on time domain cross correlation is introduced. It provides 'flow speed', a much better parameter determining whether there is a traffic jam or how fast one can cover that road under the observed situation. With regard to the 'False-Peak' problem, effect of the sequence length on correlation result is presented, together with formulas used to calculate proper sequence length both accurately and approximately. Test results demonstrate the signification of sequence length on improving cross correlation result and good accuracy suitable for estimation of road busy degree.","PeriodicalId":197058,"journal":{"name":"Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131251923","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, the classification of nonoscillatory solutions for a two-dimensional neutral difference system is considered. Sufficient and/or necessary conditions of existence for those solutions will be established.
{"title":"Classification and Existence of Non-oscillatory Solutions for Two-Dimensional Neutral Difference System","authors":"Xin Luo, Lei Guo, Z. Liu","doi":"10.1109/SNPD.2007.344","DOIUrl":"https://doi.org/10.1109/SNPD.2007.344","url":null,"abstract":"In this paper, the classification of nonoscillatory solutions for a two-dimensional neutral difference system is considered. Sufficient and/or necessary conditions of existence for those solutions will be established.","PeriodicalId":197058,"journal":{"name":"Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127588731","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 wireless sensor networks, sensor nodes generally cooperate with each other in collecting sensing data and in-network processing according to the group communication model. Key distribution is at the heart of secure group communications. In this paper, we present a scalable, efficient and authenticated scheme for group key distribution. The proposed scheme is based on a combinatorial exclusion basis system (EBS) for efficiency and one way hash chains for authentication. It guarantees an authenticated group rekeying procedure and is efficient in terms of storage, communication and computation overheads.
{"title":"ACKDs: An Authenticated Combinatorial Key Distribution Scheme for Wireless Sensor Networks","authors":"Linchun Li, Jianhua Li, L. Tie, Jun Pan","doi":"10.1109/SNPD.2007.107","DOIUrl":"https://doi.org/10.1109/SNPD.2007.107","url":null,"abstract":"In wireless sensor networks, sensor nodes generally cooperate with each other in collecting sensing data and in-network processing according to the group communication model. Key distribution is at the heart of secure group communications. In this paper, we present a scalable, efficient and authenticated scheme for group key distribution. The proposed scheme is based on a combinatorial exclusion basis system (EBS) for efficiency and one way hash chains for authentication. It guarantees an authenticated group rekeying procedure and is efficient in terms of storage, communication and computation overheads.","PeriodicalId":197058,"journal":{"name":"Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127717457","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：