Pub Date : 2009-07-12DOI: 10.1109/ICWAPR.2009.5207457
Lin-Bo Cai, Z. Ying
Contourlet Transform provides a flexible multiresolution, local and directional image expansion and a sparse representation for two dimensional piecewise smooth signal resembling images. It overcomes the weakness of wavelet transform in dealing with high dimensional signals. In this paper, the theory of Contourlet Transform is introduced and a new approach of facial expression recognition based on Contourlet Transform is proposed. Locally Linear Embedding is then applied for feature dimensionality reduction, and Vector Support Machine is used to classify the seven expressions (anger, disgust, fear, happiness, neutral, sadness and surprise) of JAFFE database. Both Wavelet Transform and Principal Component Analysis (PCA) algorithm are carried out to compare with the approach proposed. Experimental results show that the proposed approach gets better recognition rate than both Wavelet Transform and Principal Component Analysis. The facial expression recognition based on Contourlet Transform is an effective and feasible algorithm.
{"title":"A new approach of facial expression recognition based on Contourlet Transform","authors":"Lin-Bo Cai, Z. Ying","doi":"10.1109/ICWAPR.2009.5207457","DOIUrl":"https://doi.org/10.1109/ICWAPR.2009.5207457","url":null,"abstract":"Contourlet Transform provides a flexible multiresolution, local and directional image expansion and a sparse representation for two dimensional piecewise smooth signal resembling images. It overcomes the weakness of wavelet transform in dealing with high dimensional signals. In this paper, the theory of Contourlet Transform is introduced and a new approach of facial expression recognition based on Contourlet Transform is proposed. Locally Linear Embedding is then applied for feature dimensionality reduction, and Vector Support Machine is used to classify the seven expressions (anger, disgust, fear, happiness, neutral, sadness and surprise) of JAFFE database. Both Wavelet Transform and Principal Component Analysis (PCA) algorithm are carried out to compare with the approach proposed. Experimental results show that the proposed approach gets better recognition rate than both Wavelet Transform and Principal Component Analysis. The facial expression recognition based on Contourlet Transform is an effective and feasible algorithm.","PeriodicalId":424264,"journal":{"name":"2009 International Conference on Wavelet Analysis and Pattern Recognition","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116941657","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 : 2009-07-12DOI: 10.1109/ICWAPR.2009.5207408
Xiaoping Zong, Jun Geng
A new perturbation model is proposed, and used to train BP neural network for chaotic systems in this paper. The method requires no previous knowledge about the system to be controlled, including the dimensionality of the system and location of unstable fixed points, can be extended to other chaos control. It was tested on the henon and Logistic maps, and the simulation results showed that it could make the chaos present periodic motion.
{"title":"Control chaotic systems based on BP neural network with a new perturbation","authors":"Xiaoping Zong, Jun Geng","doi":"10.1109/ICWAPR.2009.5207408","DOIUrl":"https://doi.org/10.1109/ICWAPR.2009.5207408","url":null,"abstract":"A new perturbation model is proposed, and used to train BP neural network for chaotic systems in this paper. The method requires no previous knowledge about the system to be controlled, including the dimensionality of the system and location of unstable fixed points, can be extended to other chaos control. It was tested on the henon and Logistic maps, and the simulation results showed that it could make the chaos present periodic motion.","PeriodicalId":424264,"journal":{"name":"2009 International Conference on Wavelet Analysis and Pattern Recognition","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115999677","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}
Infrared image enhancement is a research focus as well as one of the difficulties in the field of information processing. Rough sets theory is a new mathematical tool to solve the issue of ambiguity and uncertainty. Curvelet transform develops from wavelet transform and has noticeable effect in denoising and signal enhancing. Based on the features of infrared image and human visual properties and combined the rough sets theory and curvelet transform, this paper has put forward a new algorithm to enhance the weak infrared image. Based on human visual properties and noise conditional properties, this algorithm first partitions an infrared image into different sub-images in accordance with two properties: pixel gradient value and noise. Then enhance the sub-images via curvelet transforming. Experiments results have shown that this new algorithm can achieve good enhancing effect and can meet the actual needs of infrared image enhancement.
{"title":"A new algorithm of infrared image enhancement based on rough sets and curvelet transform","authors":"Jian-Hui Tan, Ao-Chang Pan, Jian Liang, Yong-hui Huang, Xiao-yan Fan, Jan-Jia Pan","doi":"10.1109/ICWAPR.2009.5207419","DOIUrl":"https://doi.org/10.1109/ICWAPR.2009.5207419","url":null,"abstract":"Infrared image enhancement is a research focus as well as one of the difficulties in the field of information processing. Rough sets theory is a new mathematical tool to solve the issue of ambiguity and uncertainty. Curvelet transform develops from wavelet transform and has noticeable effect in denoising and signal enhancing. Based on the features of infrared image and human visual properties and combined the rough sets theory and curvelet transform, this paper has put forward a new algorithm to enhance the weak infrared image. Based on human visual properties and noise conditional properties, this algorithm first partitions an infrared image into different sub-images in accordance with two properties: pixel gradient value and noise. Then enhance the sub-images via curvelet transforming. Experiments results have shown that this new algorithm can achieve good enhancing effect and can meet the actual needs of infrared image enhancement.","PeriodicalId":424264,"journal":{"name":"2009 International Conference on Wavelet Analysis and Pattern Recognition","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117158874","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 : 2009-07-12DOI: 10.1109/ICWAPR.2009.5207453
Qingjiang Chen, Z. An
In this paper, we introduce a class of vector-valued wavelet packets of space L2(Rs,Cv), which are generalizations of multivariate wavelet packets. A procedure for constructing a class of biorthogonal vector-valued higher-dimensional wavelet packets is presented and their biorthogonality properties are characterized by virtue of matrix theory, time-frequency analysis method, and operator theory. Three biorthogonality formu-las regarding these wavelet packets are derived. Moreover, it is shown how to obtain new Riesz bases of space L2(Rs,Cv) from these wavelet packets.
{"title":"The survey of biorthogonal vector-valued multivariate wavelet packets with nine-scale","authors":"Qingjiang Chen, Z. An","doi":"10.1109/ICWAPR.2009.5207453","DOIUrl":"https://doi.org/10.1109/ICWAPR.2009.5207453","url":null,"abstract":"In this paper, we introduce a class of vector-valued wavelet packets of space L<sup>2</sup>(R<sup>s</sup>,C<sup>v</sup>), which are generalizations of multivariate wavelet packets. A procedure for constructing a class of biorthogonal vector-valued higher-dimensional wavelet packets is presented and their biorthogonality properties are characterized by virtue of matrix theory, time-frequency analysis method, and operator theory. Three biorthogonality formu-las regarding these wavelet packets are derived. Moreover, it is shown how to obtain new Riesz bases of space L<sup>2</sup>(R<sup>s</sup>,C<sup>v</sup>) from these wavelet packets.","PeriodicalId":424264,"journal":{"name":"2009 International Conference on Wavelet Analysis and Pattern Recognition","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117209729","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 : 2009-07-12DOI: 10.1109/ICWAPR.2009.5207414
Bei-Bei Zhu, Zhao-Wei Shang, Feng Zhang, Bo Yuan
In order to enhance the accuracy of Chinese off-line handwriting recognition, a new method based on the pyramidal dual-tree directional filter bank (PDTDFB) was presented. According to multi-resolution, arbitrarily high direction resolution, low redundant ratio and efficient implementation properties, the PDTDFB transform can effectively capture more edges and contours in image. Using the extracting features with GDD model to measure the KL distance, we get the image retrieval precision rate. In comparison to the scalar wavelet transform, the complex wavelet transform (CWT) and Contourlet transform, the method increases the accuracy about 22.3%, 7.5%, 2.3%, separately.
{"title":"Chinese handwriting-based writer identiication with PDTDFB transform","authors":"Bei-Bei Zhu, Zhao-Wei Shang, Feng Zhang, Bo Yuan","doi":"10.1109/ICWAPR.2009.5207414","DOIUrl":"https://doi.org/10.1109/ICWAPR.2009.5207414","url":null,"abstract":"In order to enhance the accuracy of Chinese off-line handwriting recognition, a new method based on the pyramidal dual-tree directional filter bank (PDTDFB) was presented. According to multi-resolution, arbitrarily high direction resolution, low redundant ratio and efficient implementation properties, the PDTDFB transform can effectively capture more edges and contours in image. Using the extracting features with GDD model to measure the KL distance, we get the image retrieval precision rate. In comparison to the scalar wavelet transform, the complex wavelet transform (CWT) and Contourlet transform, the method increases the accuracy about 22.3%, 7.5%, 2.3%, separately.","PeriodicalId":424264,"journal":{"name":"2009 International Conference on Wavelet Analysis and Pattern Recognition","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124798656","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 : 2009-07-12DOI: 10.1109/ICWAPR.2009.5207405
Shengli Zhao, Yan Liu
An evolutionary neural network method of displacement back analysis on supporting structure of deep foundation pit is proposed to search the optimal mechanical parameters. First, the BP network replaces the time-consuming finite element method to establish the non-linear relationship between the values of deep foundation pit mechanical parameters and displacement of its supporting structure, then genetic algorithm is used as an optimization method to search the optimal mechanical parameters in their global ranges. Application of this methodology is illustrated with a numerical example and reasonable results are yielded.
{"title":"Displacement back analysis on supporting structure of deep foundation pit based on evolutionary neural nrtwork","authors":"Shengli Zhao, Yan Liu","doi":"10.1109/ICWAPR.2009.5207405","DOIUrl":"https://doi.org/10.1109/ICWAPR.2009.5207405","url":null,"abstract":"An evolutionary neural network method of displacement back analysis on supporting structure of deep foundation pit is proposed to search the optimal mechanical parameters. First, the BP network replaces the time-consuming finite element method to establish the non-linear relationship between the values of deep foundation pit mechanical parameters and displacement of its supporting structure, then genetic algorithm is used as an optimization method to search the optimal mechanical parameters in their global ranges. Application of this methodology is illustrated with a numerical example and reasonable results are yielded.","PeriodicalId":424264,"journal":{"name":"2009 International Conference on Wavelet Analysis and Pattern Recognition","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128890382","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 : 2009-07-12DOI: 10.1109/ICWAPR.2009.5207496
Jinru Wang
We consider the problem of determining an unknown source, which depends only on the spatial variable, in a diffusion equation. This is an ill-posed problem. For a reconstruction of the solution from indirect data, the dual least squares method generated by the family of Shannon wavelet subspaces is applied. Moreover, a certain simple nonlinear modification of the method based on local refinements of the wavelet expansion of the noisy data is investigated.
{"title":"Wavelet soft-threshold method for determining an unknown source in a diffusion equation","authors":"Jinru Wang","doi":"10.1109/ICWAPR.2009.5207496","DOIUrl":"https://doi.org/10.1109/ICWAPR.2009.5207496","url":null,"abstract":"We consider the problem of determining an unknown source, which depends only on the spatial variable, in a diffusion equation. This is an ill-posed problem. For a reconstruction of the solution from indirect data, the dual least squares method generated by the family of Shannon wavelet subspaces is applied. Moreover, a certain simple nonlinear modification of the method based on local refinements of the wavelet expansion of the noisy data is investigated.","PeriodicalId":424264,"journal":{"name":"2009 International Conference on Wavelet Analysis and Pattern Recognition","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130259926","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 : 2009-07-12DOI: 10.1109/ICWAPR.2009.5207463
Huai-xiang Zhang, Feng Wang, Bo Zhang
The successful application of fuzzy control largely depends on some subjectively decided parameters, such as fuzzy membership functions. In this paper, Genetic learning and turning based on real-coded genetic algorithm is proposed to automatically design and optimize the fuzzy membership function's parameters. An advantage framework, which can achieve a trade-off between execution time and optimized membership function, is introduced. By using this method, the subjectivity and blindness in the process of designing the input and output membership functions are avoided. The optimized fuzzy logic controller has been compared with the traditional one and the results demonstrate that control performance of the proposed fuzzy logic control is greatly improved.
{"title":"Genetic optimization of fuzzy membership functions","authors":"Huai-xiang Zhang, Feng Wang, Bo Zhang","doi":"10.1109/ICWAPR.2009.5207463","DOIUrl":"https://doi.org/10.1109/ICWAPR.2009.5207463","url":null,"abstract":"The successful application of fuzzy control largely depends on some subjectively decided parameters, such as fuzzy membership functions. In this paper, Genetic learning and turning based on real-coded genetic algorithm is proposed to automatically design and optimize the fuzzy membership function's parameters. An advantage framework, which can achieve a trade-off between execution time and optimized membership function, is introduced. By using this method, the subjectivity and blindness in the process of designing the input and output membership functions are avoided. The optimized fuzzy logic controller has been compared with the traditional one and the results demonstrate that control performance of the proposed fuzzy logic control is greatly improved.","PeriodicalId":424264,"journal":{"name":"2009 International Conference on Wavelet Analysis and Pattern Recognition","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131742920","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 : 2009-07-12DOI: 10.1109/ICWAPR.2009.5207412
Zhenghong Huang
Based on the dyadic wavelet transform, the threshold and threshold function are obtained adaptive with the decomposition of the dyadic wavelet coefficient by to improve of the lower bound error the noise threshold, and layered processing for threshold function. The noise mixed image was separated denoising by independent component analysis. Experiments show that the proposed method improves the signal-to-noise rate. Moreover, It's better the image precision.
{"title":"Image denoising by independent component analysis based on dyadic wavelet transform","authors":"Zhenghong Huang","doi":"10.1109/ICWAPR.2009.5207412","DOIUrl":"https://doi.org/10.1109/ICWAPR.2009.5207412","url":null,"abstract":"Based on the dyadic wavelet transform, the threshold and threshold function are obtained adaptive with the decomposition of the dyadic wavelet coefficient by to improve of the lower bound error the noise threshold, and layered processing for threshold function. The noise mixed image was separated denoising by independent component analysis. Experiments show that the proposed method improves the signal-to-noise rate. Moreover, It's better the image precision.","PeriodicalId":424264,"journal":{"name":"2009 International Conference on Wavelet Analysis and Pattern Recognition","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122199041","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 : 2009-07-12DOI: 10.1109/ICWAPR.2009.5207447
Zheng-Wei Shen, Wei-Wei Liao, Yan Shen
A new blind watermarking algorithm based on Henon chaos system and lifting scheme wavelet is proposed. Two-dimensional reversible nonlinear Henon chaos system that is dealt with mould operation is utilized to scramble the watermarking images by chain type; then the scrambling watermarking is embedded into the lifting scheme wavelet coefficients using the pseudorandom of the two-dimensional Henon chaotic sequence. This watermarking embedding algorithm optimally utilizes the pseudorandom of the Henon chaos system, and also the embedding position is selected more simply and reasonably. All parameters such as controlling parameter of Henon chaos system x0, y0, z0 and embedding intensity parameter S are encrypting key which further increase the security of the watermarking algorithm. Meanwhile, the different selection of embedding intensity parameter can easily balance the invisible and the robust of the watermarking. Experimental results show that this method is invisible and robust against some usual attacks such as JPEG, cropping, adding noise, filtering and so on.
{"title":"Blind watermarking algorithm based on henon chaos system and lifting scheme wavelet","authors":"Zheng-Wei Shen, Wei-Wei Liao, Yan Shen","doi":"10.1109/ICWAPR.2009.5207447","DOIUrl":"https://doi.org/10.1109/ICWAPR.2009.5207447","url":null,"abstract":"A new blind watermarking algorithm based on Henon chaos system and lifting scheme wavelet is proposed. Two-dimensional reversible nonlinear Henon chaos system that is dealt with mould operation is utilized to scramble the watermarking images by chain type; then the scrambling watermarking is embedded into the lifting scheme wavelet coefficients using the pseudorandom of the two-dimensional Henon chaotic sequence. This watermarking embedding algorithm optimally utilizes the pseudorandom of the Henon chaos system, and also the embedding position is selected more simply and reasonably. All parameters such as controlling parameter of Henon chaos system x0, y0, z0 and embedding intensity parameter S are encrypting key which further increase the security of the watermarking algorithm. Meanwhile, the different selection of embedding intensity parameter can easily balance the invisible and the robust of the watermarking. Experimental results show that this method is invisible and robust against some usual attacks such as JPEG, cropping, adding noise, filtering and so on.","PeriodicalId":424264,"journal":{"name":"2009 International Conference on Wavelet Analysis and Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122293640","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：