The combination of biometrics and cryptography is a promising information security technique which offers an efficient way to protect the biometric template, as well as to facilitate user authentication and key management. We propose a key-binding scheme based on iris data, in which reliable region is selected to reduce the intra-class variation, and error control technique that combines RS and convolutional codes is used to increase the key length. The scheme does not reveal any significant information about the key and the original iris template, and the system achieves a false rejection rate (FRR) of less than 0.5% with the key length of 218 bits.
{"title":"Combination of Iris Recognition and Cryptography for Information Security","authors":"Long Zhang, Zhenan Sun, T. Tan, Shungeng Hu","doi":"10.1109/CCPR.2008.65","DOIUrl":"https://doi.org/10.1109/CCPR.2008.65","url":null,"abstract":"The combination of biometrics and cryptography is a promising information security technique which offers an efficient way to protect the biometric template, as well as to facilitate user authentication and key management. We propose a key-binding scheme based on iris data, in which reliable region is selected to reduce the intra-class variation, and error control technique that combines RS and convolutional codes is used to increase the key length. The scheme does not reveal any significant information about the key and the original iris template, and the system achieves a false rejection rate (FRR) of less than 0.5% with the key length of 218 bits.","PeriodicalId":292956,"journal":{"name":"2008 Chinese Conference on Pattern Recognition","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115315548","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}
Aiming at the shortages of the diagnosing efficiency, applicability and knowledge acquisition ability in traditional transformer fault diagnosing methods, an immune model for diagnosing transformer fault is established in this paper by combining the strong ability of recognition and learning in the artificial immune system (AIS) with the attributes' objectively reduction of the rough set theory (RST) together. The optimal coding of the antibodies and the antigents based on RST, the algorithm in the immune model for diagnosing and learning is analyzed in detail. Finally, the experimental results confirmed that this model has high diagnosis accuracy, strong robustness and good learning ability.
{"title":"An Approach to the Transformer Faults Diagnosing Based on Rough Set and Artificial Immune System","authors":"Shaomin Song, Yaonan Wang, Shengxin Yao, Min Wang","doi":"10.1109/CCPR.2008.94","DOIUrl":"https://doi.org/10.1109/CCPR.2008.94","url":null,"abstract":"Aiming at the shortages of the diagnosing efficiency, applicability and knowledge acquisition ability in traditional transformer fault diagnosing methods, an immune model for diagnosing transformer fault is established in this paper by combining the strong ability of recognition and learning in the artificial immune system (AIS) with the attributes' objectively reduction of the rough set theory (RST) together. The optimal coding of the antibodies and the antigents based on RST, the algorithm in the immune model for diagnosing and learning is analyzed in detail. Finally, the experimental results confirmed that this model has high diagnosis accuracy, strong robustness and good learning ability.","PeriodicalId":292956,"journal":{"name":"2008 Chinese Conference on Pattern Recognition","volume":"226 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132321883","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}
Traditional planar shape representations cannot efficiently solve some problems such as recognition under occlusion, reconstruction and partial matching. In this paper, an improved shape representation by the extraction of contour curvature is presented based on the invariance of curvature. Then the invariance and discrete approximation solution are demonstrated. Finally the reconstruction method to the contour and a new matching approach based on improved KMP (D. E. Knuth, V. R. Pratt and J. H. Morris) algorithm are proposed. Experiments illustrate the good performance of our approach to classification, occluded objects recognition and partial matching problems.
传统的平面形状表示不能有效地解决遮挡、重构和部分匹配下的识别问题。本文在曲率不变性的基础上，提出了一种通过提取轮廓曲率来改进形状表示的方法。然后证明了该方法的不变性和离散逼近解。最后，提出了一种基于改进KMP (D. E. Knuth, V. R. Pratt和J. H. Morris)算法的轮廓重建方法和一种新的匹配方法。实验证明了该方法在分类、遮挡物识别和部分匹配问题上的良好性能。
{"title":"An Improved Curvature Coding For Planar Shape Representation","authors":"Ke-Hua Guo, Jing-yu Yang","doi":"10.1109/CCPR.2008.30","DOIUrl":"https://doi.org/10.1109/CCPR.2008.30","url":null,"abstract":"Traditional planar shape representations cannot efficiently solve some problems such as recognition under occlusion, reconstruction and partial matching. In this paper, an improved shape representation by the extraction of contour curvature is presented based on the invariance of curvature. Then the invariance and discrete approximation solution are demonstrated. Finally the reconstruction method to the contour and a new matching approach based on improved KMP (D. E. Knuth, V. R. Pratt and J. H. Morris) algorithm are proposed. Experiments illustrate the good performance of our approach to classification, occluded objects recognition and partial matching problems.","PeriodicalId":292956,"journal":{"name":"2008 Chinese Conference on Pattern Recognition","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132409135","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}
Template tracking based on the space transformation model can usually be reduced to solve a nonlinear least squares optimization problem over a Lie manifold of parameters. The algorithm on the vector space has more limitations when it concerns the nonlinear projective warps. Exploiting the special structure of Lie manifolds allows one to devise a method for optimizing on Lie manifolds in a computationally efficient manner. The mapping between a Lie group and its Lie algebra can make us to utilize the specific properties of the target tracking to propose a second-order minimization tracking method. This approach needs not calculating the Hessian matrix and reduces the computation complexity. The comparative experiments with the algorithm based on the vector space and the Gauss-Newton algorithm based on the Lie algebra parameterization validate the feasibility and high effectiveness of our method.
{"title":"Projective Tracking Based on Second-Order Optimization on Lie Manifolds","authors":"Guangwei Li, Yunpeng Liu, Jian Yin, Zelin Shi","doi":"10.1109/CCPR.2008.46","DOIUrl":"https://doi.org/10.1109/CCPR.2008.46","url":null,"abstract":"Template tracking based on the space transformation model can usually be reduced to solve a nonlinear least squares optimization problem over a Lie manifold of parameters. The algorithm on the vector space has more limitations when it concerns the nonlinear projective warps. Exploiting the special structure of Lie manifolds allows one to devise a method for optimizing on Lie manifolds in a computationally efficient manner. The mapping between a Lie group and its Lie algebra can make us to utilize the specific properties of the target tracking to propose a second-order minimization tracking method. This approach needs not calculating the Hessian matrix and reduces the computation complexity. The comparative experiments with the algorithm based on the vector space and the Gauss-Newton algorithm based on the Lie algebra parameterization validate the feasibility and high effectiveness of our method.","PeriodicalId":292956,"journal":{"name":"2008 Chinese Conference on Pattern Recognition","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131550667","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}
This paper introduces a new concept of designing a discriminant analysis method (discriminator), which starts from a local mean based nearest neighbor (LM-NN) classifier and uses its decision rule to direct the design of a discriminator. The derived discriminator, called local mean based nearest neighbor discriminator (LM-NND), matches the LM-NN classifier optimally in theory. The proposed LM-NND method is evaluated using the CENPARMI handwritten numeral database, the ETH80 object category database and the PolyU Palmprint database. The experimental results demonstrate the effectiveness of LM-NND and the LM-NN classifier based pattern recognition system.
{"title":"New Concept for Discriminator Design: From Classifier to Discriminator","authors":"Jian Yang, Jing-yu Yang, Zhong Jin","doi":"10.1109/CCPR.2008.13","DOIUrl":"https://doi.org/10.1109/CCPR.2008.13","url":null,"abstract":"This paper introduces a new concept of designing a discriminant analysis method (discriminator), which starts from a local mean based nearest neighbor (LM-NN) classifier and uses its decision rule to direct the design of a discriminator. The derived discriminator, called local mean based nearest neighbor discriminator (LM-NND), matches the LM-NN classifier optimally in theory. The proposed LM-NND method is evaluated using the CENPARMI handwritten numeral database, the ETH80 object category database and the PolyU Palmprint database. The experimental results demonstrate the effectiveness of LM-NND and the LM-NN classifier based pattern recognition system.","PeriodicalId":292956,"journal":{"name":"2008 Chinese Conference on Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131005124","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}
Road identification and detection is the essential problem to be solved in intelligent vehicle systems. As the complexity dimension of the surrounding environment increases, road recognition becomes much harder under different interferences. To increment the robustness and interference immunity, a diffused region of Hough based road detection algorithm is proposed in this paper. This algorithm incorporates the global information of road shape, the assistance usage of the diffused region pixels around the road edges in the feature space. Meanwhile, the computing complexity can be decreased and the real-time ability can be increased with the aid of some pre-knowledge and estimated orientation parameters through additional sensor modules. Experiments with images sampled in our system proved the effectiveness and applicability of this method.
{"title":"Diffused Region of Hough Method Based Road Detection Algorithm","authors":"Lei Shi, Jianfeng Lu, Jing-yu Yang","doi":"10.1109/CCPR.2008.92","DOIUrl":"https://doi.org/10.1109/CCPR.2008.92","url":null,"abstract":"Road identification and detection is the essential problem to be solved in intelligent vehicle systems. As the complexity dimension of the surrounding environment increases, road recognition becomes much harder under different interferences. To increment the robustness and interference immunity, a diffused region of Hough based road detection algorithm is proposed in this paper. This algorithm incorporates the global information of road shape, the assistance usage of the diffused region pixels around the road edges in the feature space. Meanwhile, the computing complexity can be decreased and the real-time ability can be increased with the aid of some pre-knowledge and estimated orientation parameters through additional sensor modules. Experiments with images sampled in our system proved the effectiveness and applicability of this method.","PeriodicalId":292956,"journal":{"name":"2008 Chinese Conference on Pattern Recognition","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129586968","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}
This paper makes an attempt to analyze the local feature structure of iris texture information based on the barycenter distance of new non-separable wavelet. When preprocessed, the annular iris is normalized into a rectangular block. Several non-separable wavelet filters are used to capture the iris texture. In every filtered subband coefficients, we extract a certain number of largest positive coefficients and smallest negative coefficients that can represent the local texture most effectively in each subband. The barycenter of these positive coefficients in each subband is called positive barycenter, and the barycenter of negative coefficients is called negative barycenter. Then, the vector from negative barycenter to positive one is called barycenter distance vector, which is regarded as the iris feature vector. Iris feature matching is based on the similarity of the vectors. Experimental results on public databases show that the performance of the proposed method is as good as Daugman's method, and our method is more robust than Daugman's method to rotation transform in small scale.
{"title":"Iris Recognition Based on the Barycenter Distance Vector of New Non-Separable Wavelet","authors":"Jing Huang, Xinge You, Y. Tang","doi":"10.1109/CCPR.2008.67","DOIUrl":"https://doi.org/10.1109/CCPR.2008.67","url":null,"abstract":"This paper makes an attempt to analyze the local feature structure of iris texture information based on the barycenter distance of new non-separable wavelet. When preprocessed, the annular iris is normalized into a rectangular block. Several non-separable wavelet filters are used to capture the iris texture. In every filtered subband coefficients, we extract a certain number of largest positive coefficients and smallest negative coefficients that can represent the local texture most effectively in each subband. The barycenter of these positive coefficients in each subband is called positive barycenter, and the barycenter of negative coefficients is called negative barycenter. Then, the vector from negative barycenter to positive one is called barycenter distance vector, which is regarded as the iris feature vector. Iris feature matching is based on the similarity of the vectors. Experimental results on public databases show that the performance of the proposed method is as good as Daugman's method, and our method is more robust than Daugman's method to rotation transform in small scale.","PeriodicalId":292956,"journal":{"name":"2008 Chinese Conference on Pattern Recognition","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127088106","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}
The modeling and rendering of real material properties highly rely on precise data acquisition. However, it is fairly hard to gather and model the bidirectional reflectance distribution function (BRDF), which indicates the properties of real material properties. This report presents the gathering data by BRDF on the basis of linear-light source reflector. By optimizing the table of linear-light source reflector, it can more precisely recover the correlation parameter of Ward model in order to be beneficial for real material properties modeling, and construct the spatial varying BRDF (SVBRDF). The results of experiment demonstrate that BRDF data gathering method is simple, highly active, as well as keeps results accurate and precise.
{"title":"A Method for Reflectometry Attribute Modeling Based on Linear Light Source","authors":"Ruijun Liu, Yue Qi, Yong Hu, Xukun Shen","doi":"10.1109/CCPR.2008.28","DOIUrl":"https://doi.org/10.1109/CCPR.2008.28","url":null,"abstract":"The modeling and rendering of real material properties highly rely on precise data acquisition. However, it is fairly hard to gather and model the bidirectional reflectance distribution function (BRDF), which indicates the properties of real material properties. This report presents the gathering data by BRDF on the basis of linear-light source reflector. By optimizing the table of linear-light source reflector, it can more precisely recover the correlation parameter of Ward model in order to be beneficial for real material properties modeling, and construct the spatial varying BRDF (SVBRDF). The results of experiment demonstrate that BRDF data gathering method is simple, highly active, as well as keeps results accurate and precise.","PeriodicalId":292956,"journal":{"name":"2008 Chinese Conference on Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130800190","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}
This study investigates the domain adaptation problem for nature language processing tasks in the distributional view. A novel method is proposed for domain adaptation based on the hybrid model which combines the discriminative model with the generative model. The advantage of the discriminative model is to have lower asymptotic error, while the advantage of the generative model can easily incorporate the unlabeled data for better generalization performance. The hybrid model can integrate their advantages. For domain transfer, the proposed method exploits the difference of the distributions in different domains to adjust the weights of the instances in the training set so that the source labeled data is more adaptive to the target domain. Experimental results on several NLP tasks in different domains indicate that our method outperforms both the traditional supervised learning and the semi-supervised method.
{"title":"Domain Adaptation in NLP Based on Hybrid Generative and Discriminative Model","authors":"Kang Liu, Jun Zhao","doi":"10.1109/CCPR.2008.11","DOIUrl":"https://doi.org/10.1109/CCPR.2008.11","url":null,"abstract":"This study investigates the domain adaptation problem for nature language processing tasks in the distributional view. A novel method is proposed for domain adaptation based on the hybrid model which combines the discriminative model with the generative model. The advantage of the discriminative model is to have lower asymptotic error, while the advantage of the generative model can easily incorporate the unlabeled data for better generalization performance. The hybrid model can integrate their advantages. For domain transfer, the proposed method exploits the difference of the distributions in different domains to adjust the weights of the instances in the training set so that the source labeled data is more adaptive to the target domain. Experimental results on several NLP tasks in different domains indicate that our method outperforms both the traditional supervised learning and the semi-supervised method.","PeriodicalId":292956,"journal":{"name":"2008 Chinese Conference on Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130800320","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}
Ear detection is the most important step of an ear recognition system, and the detection effect of this step directly affects the performance of the whole recognition system. according to the structural characteristics of the ear itself, this paper makes improvement on the traditional AdaBoost algorithm in view of its deficiency. There are three key contributions in this paper. The first contribution is a method which can affect the emphasis point of the detector performance in order to reduce the false alarm rate, by means of changing the weight distribution of weak classifiers.The second is the introduction of a new parameter called elimination threshold ,which can improve the robustness of the detector and prevent over fitting. With the detector that we finally obtained, we test on the database of CAS-PEAL and the other two detection databases. The test results an upwards of 97% hit rate, the experimental results indicate that the ear detecting system in this paper has good detection effect. The third contribution is we designed an ear detection system of DSP and gained a good result of practical application.
{"title":"Ear Detection Based on Improved AdaBoost Algorithm","authors":"Wenjuan Li, Zhichun Mu","doi":"10.1109/CCPR.2008.69","DOIUrl":"https://doi.org/10.1109/CCPR.2008.69","url":null,"abstract":"Ear detection is the most important step of an ear recognition system, and the detection effect of this step directly affects the performance of the whole recognition system. according to the structural characteristics of the ear itself, this paper makes improvement on the traditional AdaBoost algorithm in view of its deficiency. There are three key contributions in this paper. The first contribution is a method which can affect the emphasis point of the detector performance in order to reduce the false alarm rate, by means of changing the weight distribution of weak classifiers.The second is the introduction of a new parameter called elimination threshold ,which can improve the robustness of the detector and prevent over fitting. With the detector that we finally obtained, we test on the database of CAS-PEAL and the other two detection databases. The test results an upwards of 97% hit rate, the experimental results indicate that the ear detecting system in this paper has good detection effect. The third contribution is we designed an ear detection system of DSP and gained a good result of practical application.","PeriodicalId":292956,"journal":{"name":"2008 Chinese Conference on Pattern Recognition","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130970883","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：