Pub Date : 2014-04-26DOI: 10.1109/ICIST.2014.6920544
Na Li, Xiangyang Zeng, Zhifeng Li, Y. Qiao, W. Jiang
I-vector is a popular feature representation technique in speaker verification systems. In this paper, we use Fishervoice algorithm in combination with i-vector feature representation to improve speaker verification performance. By applying the Fishervoice model to map the i-vector into a low-dimensional discriminant subspace, the intra-speaker variability can be reduced and the discriminative class boundary information can be emphasized for enhanced recognition performance. Experiments on NIST SRE 2008 core test task show that the proposed framework achieves 19.9% and 8.5% dramatic relative decrease in EER and minDCF metrics respectively compared to the state-of-the-art PLDA based method.
{"title":"Using Fishervoice to enhance the performance of I-vector based speaker verification system","authors":"Na Li, Xiangyang Zeng, Zhifeng Li, Y. Qiao, W. Jiang","doi":"10.1109/ICIST.2014.6920544","DOIUrl":"https://doi.org/10.1109/ICIST.2014.6920544","url":null,"abstract":"I-vector is a popular feature representation technique in speaker verification systems. In this paper, we use Fishervoice algorithm in combination with i-vector feature representation to improve speaker verification performance. By applying the Fishervoice model to map the i-vector into a low-dimensional discriminant subspace, the intra-speaker variability can be reduced and the discriminative class boundary information can be emphasized for enhanced recognition performance. Experiments on NIST SRE 2008 core test task show that the proposed framework achieves 19.9% and 8.5% dramatic relative decrease in EER and minDCF metrics respectively compared to the state-of-the-art PLDA based method.","PeriodicalId":306383,"journal":{"name":"2014 4th IEEE International Conference on Information Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132251339","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 : 2014-04-26DOI: 10.1109/ICIST.2014.6920573
Pei-kun He, Zhixin Li, Xuan Wang
This paper proposes a novel signal-to-noise ratio (SNR) estimation algorithm for orthogonal frequency division multiplexing (OFDM) systems in the doubly selective channels by inserting special preambles. The noise variance is estimated by one preamble symbol in time domain. Besides, the estimated noise variance can be utilized as initial noise power for iterative linear minimum mean square error (LMMSE) channel estimation. Simulation results show that this new algorithm is insensitive to the Doppler frequency and is robust in large Doppler frequency environments, and has a lower computational complexity than other methods.
{"title":"A low-complexity SNR estimation algorithm and channel estimation method for OFDM systems","authors":"Pei-kun He, Zhixin Li, Xuan Wang","doi":"10.1109/ICIST.2014.6920573","DOIUrl":"https://doi.org/10.1109/ICIST.2014.6920573","url":null,"abstract":"This paper proposes a novel signal-to-noise ratio (SNR) estimation algorithm for orthogonal frequency division multiplexing (OFDM) systems in the doubly selective channels by inserting special preambles. The noise variance is estimated by one preamble symbol in time domain. Besides, the estimated noise variance can be utilized as initial noise power for iterative linear minimum mean square error (LMMSE) channel estimation. Simulation results show that this new algorithm is insensitive to the Doppler frequency and is robust in large Doppler frequency environments, and has a lower computational complexity than other methods.","PeriodicalId":306383,"journal":{"name":"2014 4th IEEE International Conference on Information Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130481839","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}
Stripe noise is very common in uncooled infrared imaging systems and often severely degrades the image quality. Based on the analysis of existing methods, a new destriping method combining moment matching and interpolation was proposed. The method mainly consisted of three steps: Firstly, moment matching was used to eliminate most stripes. Then an adaptive algorithm was used to classify the left stripes into three types: one-pixel-width stripes, two-pixel-width stripes and local stripes. Finally, these left stripes were identified and removed with weighted multi-neighborhood interpolation. The algorithm was tested with IR images heavily polluted by stripe noises, and the result indicated that it could efficiently remove stripe noise and enhance the image quality significantly better than the single method discussed in literature.
{"title":"A new destriping method combining moment matching and interpolation in infrared images","authors":"Zhendong Gong, Hanbing Leng, Jianzhong Cao, Jihong Wang, Qingquan Wu, Xinming Fan, Bing Zhao, Lei Yang, Jiawen Liao","doi":"10.1109/ICIST.2014.6920504","DOIUrl":"https://doi.org/10.1109/ICIST.2014.6920504","url":null,"abstract":"Stripe noise is very common in uncooled infrared imaging systems and often severely degrades the image quality. Based on the analysis of existing methods, a new destriping method combining moment matching and interpolation was proposed. The method mainly consisted of three steps: Firstly, moment matching was used to eliminate most stripes. Then an adaptive algorithm was used to classify the left stripes into three types: one-pixel-width stripes, two-pixel-width stripes and local stripes. Finally, these left stripes were identified and removed with weighted multi-neighborhood interpolation. The algorithm was tested with IR images heavily polluted by stripe noises, and the result indicated that it could efficiently remove stripe noise and enhance the image quality significantly better than the single method discussed in literature.","PeriodicalId":306383,"journal":{"name":"2014 4th IEEE International Conference on Information Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131639569","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 : 2014-04-26DOI: 10.1109/ICIST.2014.6920394
Bing Li, Guotao Li, Weiyang Lin, P. Xu
In order to improve the low efficiency, poor product consistency and cruel working environment of current manual polishing method, a parallel polishing machine is presented. First, based on the freeform surface polishing requirement, a scheme of the automatic polishing machine is proposed, which includes a five-DOF parallel manipulator, a single DOF rotary table and a linear motion platform with a force feedback system. Next, a polishing force control model of the linear motion platform is established. Fractional order PIλDμ control method is introduced to achieve force-displacement hybrid control. Finally, the parallel polishing machine is developed and a constant force polishing experiment is conducted. The experimental results display that parallel polishing machine is capable of improving the roughness of the surface of the manufactured part from level 9 precision to level 11 precision.
{"title":"Design and constant force control of a parallel polishing machine","authors":"Bing Li, Guotao Li, Weiyang Lin, P. Xu","doi":"10.1109/ICIST.2014.6920394","DOIUrl":"https://doi.org/10.1109/ICIST.2014.6920394","url":null,"abstract":"In order to improve the low efficiency, poor product consistency and cruel working environment of current manual polishing method, a parallel polishing machine is presented. First, based on the freeform surface polishing requirement, a scheme of the automatic polishing machine is proposed, which includes a five-DOF parallel manipulator, a single DOF rotary table and a linear motion platform with a force feedback system. Next, a polishing force control model of the linear motion platform is established. Fractional order PIλDμ control method is introduced to achieve force-displacement hybrid control. Finally, the parallel polishing machine is developed and a constant force polishing experiment is conducted. The experimental results display that parallel polishing machine is capable of improving the roughness of the surface of the manufactured part from level 9 precision to level 11 precision.","PeriodicalId":306383,"journal":{"name":"2014 4th IEEE International Conference on Information Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130735701","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 : 2014-04-26DOI: 10.1109/ICIST.2014.6920538
Jianping Zheng, Juan Tao, Jinfang Dou, B. Bai
In this paper, the sphere decoding (SD) detector for the generalized space-time shift keying (G-STSK) scheme is developed to reduce the computational complexity of the optimal detector. The proposed SD detector consists of a series of SD algorithms with each one associated with an activated dispersion matrix pattern. Specifically, first, a lower bound of the distance measure for each possible activated dispersion matrix pattern is proposed. Then, SD algorithms are performed successively after rearranging these patterns in the order of non-decreasing lower bound. Furthermore, the list SD detector is also presented which can be employed as the soft detector in the turbo receiver for the coded G-STSK scheme. Simulation results are provided to corroborate the proposed detectors.
{"title":"Sphere decoding for generalized space-time shift keying","authors":"Jianping Zheng, Juan Tao, Jinfang Dou, B. Bai","doi":"10.1109/ICIST.2014.6920538","DOIUrl":"https://doi.org/10.1109/ICIST.2014.6920538","url":null,"abstract":"In this paper, the sphere decoding (SD) detector for the generalized space-time shift keying (G-STSK) scheme is developed to reduce the computational complexity of the optimal detector. The proposed SD detector consists of a series of SD algorithms with each one associated with an activated dispersion matrix pattern. Specifically, first, a lower bound of the distance measure for each possible activated dispersion matrix pattern is proposed. Then, SD algorithms are performed successively after rearranging these patterns in the order of non-decreasing lower bound. Furthermore, the list SD detector is also presented which can be employed as the soft detector in the turbo receiver for the coded G-STSK scheme. Simulation results are provided to corroborate the proposed detectors.","PeriodicalId":306383,"journal":{"name":"2014 4th IEEE International Conference on Information Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130739222","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 : 2014-04-26DOI: 10.1109/ICIST.2014.6920511
Shaoyan He, Shun’er Chen, Haotian Zhai, Weiping Liu
As one of important carriers of the traditional Chinese painting, rice paper has attracted wide attention. Current studies of rice paper, which have described some of rice paper's features, however, are confined to empirical macroscopic features and mechanical properties analysis. Any of the methods mentioned above cannot characterize the structural features of rice paper accurately and quantitatively, and cannot distinguish between different kinds of rice paper either. To solve these problems, we propose a novel approach for rice paper feature analysis based on texture parameter statistics of multispectral images in this paper. The multispectral imaging system is applied to obtain rice paper's spectral images under different band channels. And then texture parameter statistics are used to form a feature vector which is able to digitalize rice paper's feature. To evaluate the accuracy of the feature vectors, they are entered into the support vector machine(SVM) classifier for rice paper classification. Results show that under 550nm spectral band which is just the center of visible spectrum, rice paper's differentiation feature is pronounced most, and under that band the average accuracy is 86%. It means that application of multispectral imaging and texture analysis can describe the rice paper's feature with high accuracy.
{"title":"Rice paper feature analysis based on texture parameter statistics of multispectral imaging","authors":"Shaoyan He, Shun’er Chen, Haotian Zhai, Weiping Liu","doi":"10.1109/ICIST.2014.6920511","DOIUrl":"https://doi.org/10.1109/ICIST.2014.6920511","url":null,"abstract":"As one of important carriers of the traditional Chinese painting, rice paper has attracted wide attention. Current studies of rice paper, which have described some of rice paper's features, however, are confined to empirical macroscopic features and mechanical properties analysis. Any of the methods mentioned above cannot characterize the structural features of rice paper accurately and quantitatively, and cannot distinguish between different kinds of rice paper either. To solve these problems, we propose a novel approach for rice paper feature analysis based on texture parameter statistics of multispectral images in this paper. The multispectral imaging system is applied to obtain rice paper's spectral images under different band channels. And then texture parameter statistics are used to form a feature vector which is able to digitalize rice paper's feature. To evaluate the accuracy of the feature vectors, they are entered into the support vector machine(SVM) classifier for rice paper classification. Results show that under 550nm spectral band which is just the center of visible spectrum, rice paper's differentiation feature is pronounced most, and under that band the average accuracy is 86%. It means that application of multispectral imaging and texture analysis can describe the rice paper's feature with high accuracy.","PeriodicalId":306383,"journal":{"name":"2014 4th IEEE International Conference on Information Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132869049","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 : 2014-04-26DOI: 10.1109/ICIST.2014.6920555
Haitao Lin, Zhan Song
Spatially encoded structured light technique is an important means for the dynamic 3D reconstruction. This paper first present a novel designed pattern, which adopts four color elements and get a 2×2 unique window property. To detect the pattern features, i.e. the grid points, a twofold symmetry based feature detection method is investigated. The value of each pixel is firstly computed in R, G, B channels respectively. And the largest one is select to represent the pixel. By selecting the local maximum points as feature candidate, a measurement of twofold rotation symmetry is proposed to localize the grid point precisely. With comparison with some classical detectors and experiment with real human face, the robustness and accuracy of the proposed detector is demonstrated.
{"title":"A twofold symmetry based approach for the feature detection of pseudorandom color pattern","authors":"Haitao Lin, Zhan Song","doi":"10.1109/ICIST.2014.6920555","DOIUrl":"https://doi.org/10.1109/ICIST.2014.6920555","url":null,"abstract":"Spatially encoded structured light technique is an important means for the dynamic 3D reconstruction. This paper first present a novel designed pattern, which adopts four color elements and get a 2×2 unique window property. To detect the pattern features, i.e. the grid points, a twofold symmetry based feature detection method is investigated. The value of each pixel is firstly computed in R, G, B channels respectively. And the largest one is select to represent the pixel. By selecting the local maximum points as feature candidate, a measurement of twofold rotation symmetry is proposed to localize the grid point precisely. With comparison with some classical detectors and experiment with real human face, the robustness and accuracy of the proposed detector is demonstrated.","PeriodicalId":306383,"journal":{"name":"2014 4th IEEE International Conference on Information Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127223538","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 : 2014-04-26DOI: 10.1109/ICIST.2014.6920556
Chao Yang, Fang Liu, Zhan Song
Color coding is an important research topic in spatial encoded structured light sensing (SLS). In this study, we propose a novel graphical model based approach for the color pattern decoding task. For efficient color labeling, the color pattern is firstly decomposed into separate binary pattern images. With the labeled pattern elements, a unified probabilistic graphical framework is constructed to represent the pseudorandom pattern as a clique tree structure. The model contains two parts: the Conditional Random Field (CRF) is used to represent the dependences between these local decisions, and the Bayesian network (BN) is applied for the representation of background colors effect. A colorful target is experimented to demonstrate its feasibility. And the 3D reconstructed models based on the decoding results are also provided to show its robustness.
{"title":"A unified probabilistic graphical model based approach for the robust decoding of color structured light pattern","authors":"Chao Yang, Fang Liu, Zhan Song","doi":"10.1109/ICIST.2014.6920556","DOIUrl":"https://doi.org/10.1109/ICIST.2014.6920556","url":null,"abstract":"Color coding is an important research topic in spatial encoded structured light sensing (SLS). In this study, we propose a novel graphical model based approach for the color pattern decoding task. For efficient color labeling, the color pattern is firstly decomposed into separate binary pattern images. With the labeled pattern elements, a unified probabilistic graphical framework is constructed to represent the pseudorandom pattern as a clique tree structure. The model contains two parts: the Conditional Random Field (CRF) is used to represent the dependences between these local decisions, and the Bayesian network (BN) is applied for the representation of background colors effect. A colorful target is experimented to demonstrate its feasibility. And the 3D reconstructed models based on the decoding results are also provided to show its robustness.","PeriodicalId":306383,"journal":{"name":"2014 4th IEEE International Conference on Information Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114988809","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 : 2014-04-26DOI: 10.1109/ICIST.2014.6920380
Hui-dong Huangfu, Hongjin Zeng, Jun Zhong, Rui Cao, Haoliang Zhang
In this paper, the attenuation characteristics (attenuation vs microwave pulse power) of the microwave attenuator with wedge-type carbonyl iron (CI) under high power microwave (HPM) pulses are investigated. A reliable experimental platform was set up and used to measure the attenuation under HPM pulses. A database describing the attenuation dependence of the injected microwave pulse power (MPP) up to 100kW on various pulses width of 200ns to 1us and repeating frequency of 10Hz to 500Hz is created. The results indicate that (I) the attenuation decrease with the increasing of the injected MPP; (II) with the attenuation increasing, the variation of attenuation in whole injected MPP range increase; (III) the effects of different pulses width and repeating frequency on attenuation characteristics can be ignored.
{"title":"Research on attenuation characteristics of microwave attenuator under HPM pulses","authors":"Hui-dong Huangfu, Hongjin Zeng, Jun Zhong, Rui Cao, Haoliang Zhang","doi":"10.1109/ICIST.2014.6920380","DOIUrl":"https://doi.org/10.1109/ICIST.2014.6920380","url":null,"abstract":"In this paper, the attenuation characteristics (attenuation vs microwave pulse power) of the microwave attenuator with wedge-type carbonyl iron (CI) under high power microwave (HPM) pulses are investigated. A reliable experimental platform was set up and used to measure the attenuation under HPM pulses. A database describing the attenuation dependence of the injected microwave pulse power (MPP) up to 100kW on various pulses width of 200ns to 1us and repeating frequency of 10Hz to 500Hz is created. The results indicate that (I) the attenuation decrease with the increasing of the injected MPP; (II) with the attenuation increasing, the variation of attenuation in whole injected MPP range increase; (III) the effects of different pulses width and repeating frequency on attenuation characteristics can be ignored.","PeriodicalId":306383,"journal":{"name":"2014 4th IEEE International Conference on Information Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116019227","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 : 2014-04-26DOI: 10.1109/ICIST.2014.6920532
Huapeng Wu
Montgomery multiplication in finite fields has been paid more and more attention recently since it shows advantageous over regular multiplication in speeding up elliptic curve cryptography based network security protocols. In this paper, a most-significant-bit first bit-serial Montgomery multiplication algorithm in GF(2m) using weakly dual bases is proposed for the first time. Then a new bit-serial Montgomery multiplier architecture is proposed using a linear feedback shift register (LFSR). Complexity comparison has shown that the proposed multiplier is comparable to or has certain advantage over the best among the existing similar works found in the literature.
{"title":"Efficient bit-serial finite field montgomery multiplier in GF(2m)","authors":"Huapeng Wu","doi":"10.1109/ICIST.2014.6920532","DOIUrl":"https://doi.org/10.1109/ICIST.2014.6920532","url":null,"abstract":"Montgomery multiplication in finite fields has been paid more and more attention recently since it shows advantageous over regular multiplication in speeding up elliptic curve cryptography based network security protocols. In this paper, a most-significant-bit first bit-serial Montgomery multiplication algorithm in GF(2m) using weakly dual bases is proposed for the first time. Then a new bit-serial Montgomery multiplier architecture is proposed using a linear feedback shift register (LFSR). Complexity comparison has shown that the proposed multiplier is comparable to or has certain advantage over the best among the existing similar works found in the literature.","PeriodicalId":306383,"journal":{"name":"2014 4th IEEE International Conference on Information Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123436941","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：