Extracting geometric data of landmarks from fluoroscopic images plays an important role in camera calibration process of a fluoroscopic-image-based surgical navigation system. Connected components labeling is the esse...Extracting geometric data of landmarks from fluoroscopic images plays an important role in camera calibration process of a fluoroscopic-image-based surgical navigation system. Connected components labeling is the essential technique for the extraction. A new fast connected components labeling algorithm was presented. The definition of upward concave set was introduced to explain the algorithm. Feasibility and efficiency of the algorithm were verified with experiments. This algorithm performs well in labeling non-upward concave set connected components and applies to landmarks labeling well. Moreover, the proposed algorithm possesses a desirable characteristic that will facilitate the subsequent processing of fluoroscopic images.展开更多
Visual cryptography is a cryptographic technique which emerges in the information security domain in recent years. Each of the sharing sub-keys may be a stochastic noise image or a significative image with no informat...Visual cryptography is a cryptographic technique which emerges in the information security domain in recent years. Each of the sharing sub-keys may be a stochastic noise image or a significative image with no information on the original key. But a mass of sub-keys have to be saved actually, which faces the problem of inconvenient discrimination and management. This paper presents a visual cryptography scheme based on the digital signature for image discrimination and management, applying the digital signature and the time-stamp technology to the visual cryptography scheme. The scheme both solves the problem on the storage and management of the sharing sub-keys, increases the verification of image contents, thus enhances the validity of storage and management without security effect.展开更多
The threshold group signature is an important kind of signature. So far, many threshold group signature schemes have been proposed, but most of them suffer from conspiracy attack and are insecure. In this paper, a sec...The threshold group signature is an important kind of signature. So far, many threshold group signature schemes have been proposed, but most of them suffer from conspiracy attack and are insecure. In this paper, a secure threshold group signature scheme is proposed. It can not only satisfy the properties of the threshold group signature, but also withstand the conspiracy attack.展开更多
This study describes the development of a simple biometric facial recognition system, BFMT, which is designed for use in identifying individuals within a given population. The system is based on digital signatures der...This study describes the development of a simple biometric facial recognition system, BFMT, which is designed for use in identifying individuals within a given population. The system is based on digital signatures derived from facial images of human subjects. The results of the study demonstrate that a particular set of facial features from a simple two-dimensional image can yield a unique digital signature which can be used to identify a subject from a limited population within a controlled environment. The simplicity of the model upon which the system is based can result in commercial facial recognition systems that are more cost-effective to develop than those currently on the market.展开更多
A novel traffic sign recognition system is presented in this work. Firstly, the color segmentation and shape classifier based on signature feature of region are used to detect traffic signs in input video sequences. S...A novel traffic sign recognition system is presented in this work. Firstly, the color segmentation and shape classifier based on signature feature of region are used to detect traffic signs in input video sequences. Secondly, traffic sign color-image is preprocessed with gray scaling, and normalized to 64×64 size. Then, image features could be obtained by four levels DT-CWT images. Thirdly, 2DICA and nearest neighbor classifier are united to recognize traffic signs. The whole recognition algorithm is implemented for classification of 50 categories of traffic signs and its recognition accuracy reaches 90%. Comparing image representation DT-CWT with the well-established image representation like template, Gabor, and 2DICA with feature selection techniques such as PCA, LPP, 2DPCA at the same time, the results show that combination method of DT-CWT and 2DICA is useful in traffic signs recognition. Experimental results indicate that the proposed algorithm is robust, effective and accurate.展开更多
基金Supported by the Zhejiang Provincial Natural Science Foundation of China(102055)Supported by the NSF of China(10471131)Supported by the Foundation of Zhejiang Universities' Youth Teachers
文摘The problem studied in this paper is to determine e（p, C）, the minimum size of a connected graph G with given vertex number p and cut-width C.
基金Projectof Science and Technology Committee of Shanghai Municipality(No2528(3))
文摘Extracting geometric data of landmarks from fluoroscopic images plays an important role in camera calibration process of a fluoroscopic-image-based surgical navigation system. Connected components labeling is the essential technique for the extraction. A new fast connected components labeling algorithm was presented. The definition of upward concave set was introduced to explain the algorithm. Feasibility and efficiency of the algorithm were verified with experiments. This algorithm performs well in labeling non-upward concave set connected components and applies to landmarks labeling well. Moreover, the proposed algorithm possesses a desirable characteristic that will facilitate the subsequent processing of fluoroscopic images.
文摘Visual cryptography is a cryptographic technique which emerges in the information security domain in recent years. Each of the sharing sub-keys may be a stochastic noise image or a significative image with no information on the original key. But a mass of sub-keys have to be saved actually, which faces the problem of inconvenient discrimination and management. This paper presents a visual cryptography scheme based on the digital signature for image discrimination and management, applying the digital signature and the time-stamp technology to the visual cryptography scheme. The scheme both solves the problem on the storage and management of the sharing sub-keys, increases the verification of image contents, thus enhances the validity of storage and management without security effect.
基金Supported in part by the National Natural Science Foundation of China under the Grant 60172060
文摘The threshold group signature is an important kind of signature. So far, many threshold group signature schemes have been proposed, but most of them suffer from conspiracy attack and are insecure. In this paper, a secure threshold group signature scheme is proposed. It can not only satisfy the properties of the threshold group signature, but also withstand the conspiracy attack.
文摘This study describes the development of a simple biometric facial recognition system, BFMT, which is designed for use in identifying individuals within a given population. The system is based on digital signatures derived from facial images of human subjects. The results of the study demonstrate that a particular set of facial features from a simple two-dimensional image can yield a unique digital signature which can be used to identify a subject from a limited population within a controlled environment. The simplicity of the model upon which the system is based can result in commercial facial recognition systems that are more cost-effective to develop than those currently on the market.
基金Projects(90820302, 60805027) supported by the National Natural Science Foundation of ChinaProject(200805330005) supported by Research Fund for Doctoral Program of Higher Education, ChinaProject(2009FJ4030) supported by Academician Foundation of Hunan Province, China
文摘A novel traffic sign recognition system is presented in this work. Firstly, the color segmentation and shape classifier based on signature feature of region are used to detect traffic signs in input video sequences. Secondly, traffic sign color-image is preprocessed with gray scaling, and normalized to 64×64 size. Then, image features could be obtained by four levels DT-CWT images. Thirdly, 2DICA and nearest neighbor classifier are united to recognize traffic signs. The whole recognition algorithm is implemented for classification of 50 categories of traffic signs and its recognition accuracy reaches 90%. Comparing image representation DT-CWT with the well-established image representation like template, Gabor, and 2DICA with feature selection techniques such as PCA, LPP, 2DPCA at the same time, the results show that combination method of DT-CWT and 2DICA is useful in traffic signs recognition. Experimental results indicate that the proposed algorithm is robust, effective and accurate.
