Pub Date : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073415
W. Zhang, Yide Ma
In iris recognition systems, iris localization is a critical step which affects the further results definitively. Most of the traditional localization methods were time consuming and sensitive to noises. To solve the problems, we propose an algorithm which adopts a momentum based level set method to locate the pupil boundary. This method hasan advantage of decreasing the effect of local optima solutions and poor convergence dramatically, thus it could accurately describes the pupil boundary and decrease the influences of error parts. Experiment results show the iris localization under this method has a higher accuracy, and the inner iris boundary is much closer to the real one, localization results have been improved significantly.
{"title":"A new approach for iris localization based on an improved level set method","authors":"W. Zhang, Yide Ma","doi":"10.1109/ICCWAMTIP.2014.7073415","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073415","url":null,"abstract":"In iris recognition systems, iris localization is a critical step which affects the further results definitively. Most of the traditional localization methods were time consuming and sensitive to noises. To solve the problems, we propose an algorithm which adopts a momentum based level set method to locate the pupil boundary. This method hasan advantage of decreasing the effect of local optima solutions and poor convergence dramatically, thus it could accurately describes the pupil boundary and decrease the influences of error parts. Experiment results show the iris localization under this method has a higher accuracy, and the inner iris boundary is much closer to the real one, localization results have been improved significantly.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130326576","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073412
R. Shaikh, S. Deep, Jian-ping Li, Muhammad Hammad Memon, Asif Khan, K. Kumar
World dynamic situation are full of random changes which include multiple factors like audio, video and image. So cause of concurrent incident and simultaneously device performance requirement become typical for information retrieval. That make segmentation approach a method of combining feature transformation with clustering algorithm which is proposed for adequate retrieval of image, that could take input approach equally as similar platform and after function performance of analyses and processing that methodology make image, audio, video information separate and retrieve them as much clear as possible then give a best clear resultant as per certainty.
{"title":"Content factors segmentation with CBIR in real world","authors":"R. Shaikh, S. Deep, Jian-ping Li, Muhammad Hammad Memon, Asif Khan, K. Kumar","doi":"10.1109/ICCWAMTIP.2014.7073412","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073412","url":null,"abstract":"World dynamic situation are full of random changes which include multiple factors like audio, video and image. So cause of concurrent incident and simultaneously device performance requirement become typical for information retrieval. That make segmentation approach a method of combining feature transformation with clustering algorithm which is proposed for adequate retrieval of image, that could take input approach equally as similar platform and after function performance of analyses and processing that methodology make image, audio, video information separate and retrieve them as much clear as possible then give a best clear resultant as per certainty.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133694692","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073439
Yujian Wang, Kaiguo Qian
In traditional DV-Hop localization algorithm, the average estimation hop distance is greater influence for the distribution of beacon nodes, which causes high positioning error. A new algorithm is proposed to improve this disadvantage. The new improved algorithm uses the hyperbolic method to locate the unknown node position. This way eliminates the cumulative error and improves the positioning accuracy. Simulation experiments show that the positioning error of improved algorithm is better than DV-Hop algorithm that reduced by 15% or so, and the best case, the positioning error decreases to 15%, meets the demand of sensor network localization accuracy.
{"title":"An improved DV-HOP positioning algorithm based on Hop distance correction","authors":"Yujian Wang, Kaiguo Qian","doi":"10.1109/ICCWAMTIP.2014.7073439","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073439","url":null,"abstract":"In traditional DV-Hop localization algorithm, the average estimation hop distance is greater influence for the distribution of beacon nodes, which causes high positioning error. A new algorithm is proposed to improve this disadvantage. The new improved algorithm uses the hyperbolic method to locate the unknown node position. This way eliminates the cumulative error and improves the positioning accuracy. Simulation experiments show that the positioning error of improved algorithm is better than DV-Hop algorithm that reduced by 15% or so, and the best case, the positioning error decreases to 15%, meets the demand of sensor network localization accuracy.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129422269","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073380
Jing Li, Xin Yang, Liping Yao, K. Sun
This paper discusses centerline extraction algorithms for virtual cardiovascular endoscopy system. A fully automatic extraction method is proposed which is significantly enhanced from current distance mapping method. The new approach consists of four steps: preprocessing; construction of improved Distance From Boundary field; centerline extraction; mean value smoothing of centerline. Based on the proposed automatic approach, an interactive extraction method is presented in which a centerline connects specified points selected by cardiologists. This interactive approach makes the viewport closer to pathological changes in the aorta and human heart, so cardiologists can observe focuses more clearly. The two algorithms have been applied to the virtual cardiovascular endoscopy system, and the experiments prove that our methods work well in the process of auxiliary diagnosis.
{"title":"3-D centerline extraction for virtual cardiovascular endoscopy","authors":"Jing Li, Xin Yang, Liping Yao, K. Sun","doi":"10.1109/ICCWAMTIP.2014.7073380","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073380","url":null,"abstract":"This paper discusses centerline extraction algorithms for virtual cardiovascular endoscopy system. A fully automatic extraction method is proposed which is significantly enhanced from current distance mapping method. The new approach consists of four steps: preprocessing; construction of improved Distance From Boundary field; centerline extraction; mean value smoothing of centerline. Based on the proposed automatic approach, an interactive extraction method is presented in which a centerline connects specified points selected by cardiologists. This interactive approach makes the viewport closer to pathological changes in the aorta and human heart, so cardiologists can observe focuses more clearly. The two algorithms have been applied to the virtual cardiovascular endoscopy system, and the experiments prove that our methods work well in the process of auxiliary diagnosis.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116368327","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073360
Longfei Chen, Xiaomei Yang
In this paper we proposed a robust video blocking artifacts reduction method based on low-rank theory and patch grouping. We separate video sequences into low-rank parts and sparse parts in order to improve the accuracy and robustness of the matrix completion problem. A Sigma filter is applied to the sparse parts for further denoising. Experimental results show the obvious effect of proposed method on reducing both blocking artifacts and isolation noise, meanwhile our method enhances the implementation efficiency by adopting Inexact Lagrange Multiplier algorithm in matrix recovery and completion without any prediction in singular value decomposition or overlap on pixels afterwards.
{"title":"A low rank based robust video deblocking method","authors":"Longfei Chen, Xiaomei Yang","doi":"10.1109/ICCWAMTIP.2014.7073360","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073360","url":null,"abstract":"In this paper we proposed a robust video blocking artifacts reduction method based on low-rank theory and patch grouping. We separate video sequences into low-rank parts and sparse parts in order to improve the accuracy and robustness of the matrix completion problem. A Sigma filter is applied to the sparse parts for further denoising. Experimental results show the obvious effect of proposed method on reducing both blocking artifacts and isolation noise, meanwhile our method enhances the implementation efficiency by adopting Inexact Lagrange Multiplier algorithm in matrix recovery and completion without any prediction in singular value decomposition or overlap on pixels afterwards.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116517980","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073379
Bing-Li Liu, Xueyan Wang, K. Guo, Yun-Hua Zhao
Geochemical data processing plays an important role in the process of geochemical prospecting. According to the nonlinear characteristics of the geochemical data, the wavelet adaptive multi-threshold based on generalized cross-validation (GCV) criterion was adopted towards geochemical data preprocessing and good results are also achieved by validation in practical work area.
{"title":"Geochemical data processing based on wavelet de-noising","authors":"Bing-Li Liu, Xueyan Wang, K. Guo, Yun-Hua Zhao","doi":"10.1109/ICCWAMTIP.2014.7073379","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073379","url":null,"abstract":"Geochemical data processing plays an important role in the process of geochemical prospecting. According to the nonlinear characteristics of the geochemical data, the wavelet adaptive multi-threshold based on generalized cross-validation (GCV) criterion was adopted towards geochemical data preprocessing and good results are also achieved by validation in practical work area.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114683094","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073456
Xinshuo Li, Jian-Pin Li, Yuanyan Tang
The orthogonal wavelet lowpassed filters coefficients with arbitrary length are constructed in this paper. When N=2k and N= 2k-1, the general analytic constructions of orthogonal wavelet filters are put forward, respectively. The famous Daubechies filter and many other wavelet filters are tested by the proposed novel method, which is very useful for wavelet theory research and many applications areas such as pattern recognition.
{"title":"Another general analytic construction for wavelet lowpassed filters","authors":"Xinshuo Li, Jian-Pin Li, Yuanyan Tang","doi":"10.1109/ICCWAMTIP.2014.7073456","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073456","url":null,"abstract":"The orthogonal wavelet lowpassed filters coefficients with arbitrary length are constructed in this paper. When N=2k and N= 2k-1, the general analytic constructions of orthogonal wavelet filters are put forward, respectively. The famous Daubechies filter and many other wavelet filters are tested by the proposed novel method, which is very useful for wavelet theory research and many applications areas such as pattern recognition.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125873533","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073367
Hui-Yue Yu, Jun Liu, Min Wang, Shaolin Hu, R. Guo
Based on a large number of downlink telemetry data during the spacecraft on-orbit operation, the characteristic of spacecraft state change is obtained. It is of great significance to realize the safe and reliable spacecraft operation management. In order to achieve the accurate trend prediction for a spacecraft, a hybrid prediction algorithm using wavelet analysis and time series method is presented on the basis of mechanism analysis and data characteristics analysis. Firstly, wavelet analysis is introduced to make decomposition and reconstruction calculations for downlink telemetry signals, and non-stationary signal can be converted to multi-layer relatively stable decomposition sequences. Secondly, a prediction model for each decomposition level sequence is established by using the method of time series. Finally, the final prediction results can be obtained by adding the predicted value of each layer. The simulation results show that the combined model not only has higher prediction accuracy, but also have stronger adaptability for different forecast objects. The method can provide evidence for improving the validity and correctness of spacecraft data analysis and fault diagnosis.
{"title":"The trend prediction for spacecraft state based on wavelet analysis and time series method","authors":"Hui-Yue Yu, Jun Liu, Min Wang, Shaolin Hu, R. Guo","doi":"10.1109/ICCWAMTIP.2014.7073367","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073367","url":null,"abstract":"Based on a large number of downlink telemetry data during the spacecraft on-orbit operation, the characteristic of spacecraft state change is obtained. It is of great significance to realize the safe and reliable spacecraft operation management. In order to achieve the accurate trend prediction for a spacecraft, a hybrid prediction algorithm using wavelet analysis and time series method is presented on the basis of mechanism analysis and data characteristics analysis. Firstly, wavelet analysis is introduced to make decomposition and reconstruction calculations for downlink telemetry signals, and non-stationary signal can be converted to multi-layer relatively stable decomposition sequences. Secondly, a prediction model for each decomposition level sequence is established by using the method of time series. Finally, the final prediction results can be obtained by adding the predicted value of each layer. The simulation results show that the combined model not only has higher prediction accuracy, but also have stronger adaptability for different forecast objects. The method can provide evidence for improving the validity and correctness of spacecraft data analysis and fault diagnosis.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124723203","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073392
Qijin Sun, Suoju He
Recently Pac-Man game has received some attention of AI researchers. Some artificial intelligence researches have been performed with the Pac-Man game. The Monte Carlo, UCT (Upper Confidence Bound for Tree) and DTS (Dynamically Expanding UCT Tree Search) method have some good performances when used in Pac-Man game. However, these methods are based on intensive computation and so they usually could not be used in multiplayer online games. This paper discusses the advantages of Artificial Neural Network (ANN) method compared with DTS. It uses the results of DTS - called training set. The advantage of ANN is that it uses much less CPU resources than DTS. So it can be used in multiplayer online games whose AI program is running on the server, or in some other situations that require low computational intensity. This paper aims to discuss one main issue about ANN method based on the training set provided by DTS: how to implement ANN using the training set of DTS.
最近，吃豆人游戏受到了一些人工智能研究者的关注。一些人工智能研究已经在吃豆人游戏中进行了。Monte Carlo、UCT (Upper Confidence Bound for Tree)和DTS (dynamic expansion UCT Tree Search)方法在吃豆人游戏中都有很好的应用。然而，这些方法是基于密集的计算，所以它们通常不能用于多人在线游戏。本文讨论了人工神经网络(ANN)方法相对于DTS方法的优势。它使用被称为训练集的DTS的结果。ANN的优点是它比DTS使用更少的CPU资源。因此，它可以用于人工智能程序在服务器上运行的多人在线游戏，或者其他一些需要低计算强度的情况。本文旨在讨论基于DTS提供的训练集的人工神经网络方法的一个主要问题:如何利用DTS的训练集实现人工神经网络。
{"title":"Artificial neural network using the training set of DTS for Pacman game","authors":"Qijin Sun, Suoju He","doi":"10.1109/ICCWAMTIP.2014.7073392","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073392","url":null,"abstract":"Recently Pac-Man game has received some attention of AI researchers. Some artificial intelligence researches have been performed with the Pac-Man game. The Monte Carlo, UCT (Upper Confidence Bound for Tree) and DTS (Dynamically Expanding UCT Tree Search) method have some good performances when used in Pac-Man game. However, these methods are based on intensive computation and so they usually could not be used in multiplayer online games. This paper discusses the advantages of Artificial Neural Network (ANN) method compared with DTS. It uses the results of DTS - called training set. The advantage of ANN is that it uses much less CPU resources than DTS. So it can be used in multiplayer online games whose AI program is running on the server, or in some other situations that require low computational intensity. This paper aims to discuss one main issue about ANN method based on the training set provided by DTS: how to implement ANN using the training set of DTS.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124794071","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073441
P. Fan, Xinbao Liu
Non-destructive evaluation technique has been proved to be able to identify microscopic material degradation based on various nonlinear effects of ultrasonic wave propagation in structures. Wavelet transform becomes a promising method, due to its ability to analyze signal with multi-resolution. However, the damage detection results with the conventional wavelet transforms are usually dissatisfied because of the signal complexity and noises. In the present study, a novel damage feature parameter is proposed based on the signal energy of wavelet packet transform (WPT). With the proposed feature parameter, the damage detection results can be obtained. In addition, the simulation results show that the detection of crack with the present method is robust under low SNR environment.
{"title":"Ultrasonic damage detection with WPT","authors":"P. Fan, Xinbao Liu","doi":"10.1109/ICCWAMTIP.2014.7073441","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073441","url":null,"abstract":"Non-destructive evaluation technique has been proved to be able to identify microscopic material degradation based on various nonlinear effects of ultrasonic wave propagation in structures. Wavelet transform becomes a promising method, due to its ability to analyze signal with multi-resolution. However, the damage detection results with the conventional wavelet transforms are usually dissatisfied because of the signal complexity and noises. In the present study, a novel damage feature parameter is proposed based on the signal energy of wavelet packet transform (WPT). With the proposed feature parameter, the damage detection results can be obtained. In addition, the simulation results show that the detection of crack with the present method is robust under low SNR environment.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129931882","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：