{"title":"Effective multiple-features extraction for off-line SVM-based handwritten numeral recognition","authors":"Shen-Wei Lee, Hsien-Chu Wu","doi":"10.1109/ISIC.2012.6449739","DOIUrl":"https://doi.org/10.1109/ISIC.2012.6449739","url":null,"abstract":"In this paper, a multiple features extraction technique for the recognition of handwritten numbers is proposed. The proposed technique mainly extracts direction information from the structure of contours of each handwritten number and the direction information is integrated with a technique for detecting transitions among pixels and counting the number of cross lines in the lined image of offline handwritten numbers. The combinational technique used in the recognition with a Support Vector Machine (SVM) [13] classifier provides recognition rates up to 98.99%. This proposed technique also uses SVM for determining the effective features extracted from the multiple features extraction of the handwritten number recognition.","PeriodicalId":393653,"journal":{"name":"2012 International Conference on Information Security and Intelligent Control","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123714875","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}
{"title":"The high embedding steganographic method based on general multi-EMD","authors":"W. Kuo, Lih-Chyau Wuu, S. Kuo","doi":"10.1109/ISIC.2012.6449762","DOIUrl":"https://doi.org/10.1109/ISIC.2012.6449762","url":null,"abstract":"The hidden secret message capacity, stego-image quality and security are three important conditions for data hiding technology. According to these requirements, an effective security protection with high hiding capacity steganographic method based on general multi-EMD is proposed in this paper. The major contribution of this method is not to need more complicated embedded steps when the secret data is embedded and additional information when the secret data is recovered, respectively. From our simulation results, the proposed scheme not only maintains the original data hiding requirements but also achieves higher capacity than Kuo-Wang scheme.","PeriodicalId":393653,"journal":{"name":"2012 International Conference on Information Security and Intelligent Control","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125899488","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}
{"title":"Restoration of out of focus images using neural network","authors":"Hun-Chen Chen, J. Yen, Hung-Chun Chen","doi":"10.1109/ISIC.2012.6449747","DOIUrl":"https://doi.org/10.1109/ISIC.2012.6449747","url":null,"abstract":"Restoration of out of focus images is important role in imaging system. The lens defocus may cause image blurring. In this paper, a neural network approach to estimate the blur parameter for uniform out of focus blur is proposed. we estimate the parameter of defocused image in frequency domain by using circle Hough transform, and combine with neural network to have the relationship between the parameter of frequency response of out of focus image and the parameter of uniform out of focus blur model. Finally, we restore the out of focus image with its spatial continuous point spread function (PSF) and the trained neural network. The simulation result shows that the average error with the proposed estimation method is smaller than 0.48%, and more accurate than the existing methods.","PeriodicalId":393653,"journal":{"name":"2012 International Conference on Information Security and Intelligent Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129492614","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}
{"title":"Jacobian-based motion planning for climbing robots","authors":"Chien-Chou Lin, S. Dai","doi":"10.1109/ISIC.2012.6449712","DOIUrl":"https://doi.org/10.1109/ISIC.2012.6449712","url":null,"abstract":"This paper proposes a two-stage planning algorithm for 3-leg free-climbing robots. The algorithm consists of global path planner and local motion planner. Firstly, the proposed algorithm distributes climbing points to Delaunay triangle mesh. The global planner plans a sequence of Delaunay triangles from the start configuration to goal configuration. Then, the latter plans the transition configurations between two adjacent triangles of the trajectory. The local motion algorithm uses the inverse Jacobian matrix to derive the positions and angles of joints for all configurations. Since the proposed algorithm directly uses spatial information of the workspace to plan a path, it is more efficient than configuration-space based approaches. Simulation results show that the proposed algorithm works well.","PeriodicalId":393653,"journal":{"name":"2012 International Conference on Information Security and Intelligent Control","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122158688","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}
{"title":"Hybrid data deduplication in cloud environment","authors":"Chun-I Fan, Shi-Yuan Huang, Wen-Che Hsu","doi":"10.1109/ISIC.2012.6449734","DOIUrl":"https://doi.org/10.1109/ISIC.2012.6449734","url":null,"abstract":"In cloud environments, users store their data or files in cloud storage but it is not infinitely large. In order to reduce the requirement of storage and bandwidth, data deduplication has been applied. Users can share one copy of the duplicate files or data blocks to eliminate redundant data. Besides, considering the privacy of sensitive files, the users hope that the cloud server cannot know any information about those files. They often use certain encryption algorithms to protect the sensitive files before storing them in the cloud storage. Unfortunately, previous schemes have a security problem. These schemes did not satisfy semantic security. In this manuscript, we propose a hybrid data deduplication mechanism which provides a practical solution with partial semantic security.","PeriodicalId":393653,"journal":{"name":"2012 International Conference on Information Security and Intelligent Control","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132995786","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}