Pub Date : 2002-11-07DOI: 10.1109/ICDSP.2002.1028138
I. Kakadiaris, M. Papadakis, Lixin Shen, D. Kouri, D. Hoffman
In this paper, we construct a new class of deformable models using new orthogonal wavelets, named modified Hermite distributed approximating functional (m-HDAF) wavelets. The scaling functions of this new family are symmetric and the corresponding wavelets optimize their smoothness for a given number of vanishing moments. In addition, we embed these multiresolution deformable models to the physics-based deformable model framework and use them for fitting 2D and 3D data. We have performed a number of experiments with both synthetic and real data with very encouraging results.
{"title":"m-HDAF multiresolution deformable models","authors":"I. Kakadiaris, M. Papadakis, Lixin Shen, D. Kouri, D. Hoffman","doi":"10.1109/ICDSP.2002.1028138","DOIUrl":"https://doi.org/10.1109/ICDSP.2002.1028138","url":null,"abstract":"In this paper, we construct a new class of deformable models using new orthogonal wavelets, named modified Hermite distributed approximating functional (m-HDAF) wavelets. The scaling functions of this new family are symmetric and the corresponding wavelets optimize their smoothness for a given number of vanishing moments. In addition, we embed these multiresolution deformable models to the physics-based deformable model framework and use them for fitting 2D and 3D data. We have performed a number of experiments with both synthetic and real data with very encouraging results.","PeriodicalId":351073,"journal":{"name":"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121067714","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 : 2002-11-07DOI: 10.1109/ICDSP.2002.1028281
M. Gordan, Constantine Kotropoulos, I. Pitas
In this paper we propose a visual speech recognition network based on support vector machines. Each word of the dictionary is described as a temporal sequence of visemes. Each viseme is described by a support vector machine, and the temporal character of speech is modeled by integrating the support vector machines as nodes into a Viterbi decoding lattice. Experiments conducted on a small visual speech recognition task show a word recognition rate on the level of the best rates previously reported, even without training the state transition probabilities in the Viterbi lattice and using very simple features. This proves the suitability of support vector machines for visual speech recognition.
{"title":"Visual speech recognition using support vector machines","authors":"M. Gordan, Constantine Kotropoulos, I. Pitas","doi":"10.1109/ICDSP.2002.1028281","DOIUrl":"https://doi.org/10.1109/ICDSP.2002.1028281","url":null,"abstract":"In this paper we propose a visual speech recognition network based on support vector machines. Each word of the dictionary is described as a temporal sequence of visemes. Each viseme is described by a support vector machine, and the temporal character of speech is modeled by integrating the support vector machines as nodes into a Viterbi decoding lattice. Experiments conducted on a small visual speech recognition task show a word recognition rate on the level of the best rates previously reported, even without training the state transition probabilities in the Viterbi lattice and using very simple features. This proves the suitability of support vector machines for visual speech recognition.","PeriodicalId":351073,"journal":{"name":"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121097698","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 : 2002-11-07DOI: 10.1109/ICDSP.2002.1028284
Yu-Kuen Ho, Mei-Yi Wu, Jia-Hong Lee
A novel method for adaptively selecting texture features is presented. We apply statistical steganography techniques with searching for an optimal set of binary masks to extract texture features and provide the best discrimination of texture images. The extracted texture features are robust to noise attacks. Moreover, a tree structure containing the selected set of masks has been set up for classification. Experiments show that the proposed method can achieve high classification rate and also work well in a noise environment.
{"title":"Hierarchic texture classification using statistical steganography techniques","authors":"Yu-Kuen Ho, Mei-Yi Wu, Jia-Hong Lee","doi":"10.1109/ICDSP.2002.1028284","DOIUrl":"https://doi.org/10.1109/ICDSP.2002.1028284","url":null,"abstract":"A novel method for adaptively selecting texture features is presented. We apply statistical steganography techniques with searching for an optimal set of binary masks to extract texture features and provide the best discrimination of texture images. The extracted texture features are robust to noise attacks. Moreover, a tree structure containing the selected set of masks has been set up for classification. Experiments show that the proposed method can achieve high classification rate and also work well in a noise environment.","PeriodicalId":351073,"journal":{"name":"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)","volume":"453 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129484371","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 : 2002-11-07DOI: 10.1109/ICDSP.2002.1028253
S. Lefèvre, Benjamin Maillard, N. Vincent
We are dealing with segmentation of audio data in order to analyse football audio/video sequences. Audio data is divided into short sequences (typically with duration of one or half a second) which is classified into several classes (speaker, crowd and referee whistle). Every sequence can then be further analysed depending on the class it belongs to. In order to segment audio data, several methods are presented. First simple techniques are reviewed for segmentation in two classes. From the limitations of these approaches, a method based on cepstral analysis is detailed. Next we present two more complex methods dealing with 3 classes segmentation. The first one is based on hidden Markov models whereas the second one is a combination of a C-mean classifier and multidimensional hidden Markov models.
{"title":"3 classes segmentation for analysis of football audio sequences","authors":"S. Lefèvre, Benjamin Maillard, N. Vincent","doi":"10.1109/ICDSP.2002.1028253","DOIUrl":"https://doi.org/10.1109/ICDSP.2002.1028253","url":null,"abstract":"We are dealing with segmentation of audio data in order to analyse football audio/video sequences. Audio data is divided into short sequences (typically with duration of one or half a second) which is classified into several classes (speaker, crowd and referee whistle). Every sequence can then be further analysed depending on the class it belongs to. In order to segment audio data, several methods are presented. First simple techniques are reviewed for segmentation in two classes. From the limitations of these approaches, a method based on cepstral analysis is detailed. Next we present two more complex methods dealing with 3 classes segmentation. The first one is based on hidden Markov models whereas the second one is a combination of a C-mean classifier and multidimensional hidden Markov models.","PeriodicalId":351073,"journal":{"name":"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129522516","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 : 2002-11-07DOI: 10.1109/ICDSP.2002.1028234
E. Christopoulou, A. Skodras, A. Georgakilas
By decomposing a time series into time-frequency space, one is able to determine both the dominant mode of variability and how those modes vary in time. We take advantage of this property of the wavelet analysis in order to examine the temporal variation of the period of the umbral oscillations using ground-based observations of the solar atmosphere. We use this real-life signal in order to test the capabilities of different wavelets and to see the problems that arise in analyzing such a signal. We use the continuous wavelet transform in order to perform the analysis and the "a/spl grave/ trous" algorithm as a detrending tool.
{"title":"Time series analysis of sunspot oscillations using the wavelet transform","authors":"E. Christopoulou, A. Skodras, A. Georgakilas","doi":"10.1109/ICDSP.2002.1028234","DOIUrl":"https://doi.org/10.1109/ICDSP.2002.1028234","url":null,"abstract":"By decomposing a time series into time-frequency space, one is able to determine both the dominant mode of variability and how those modes vary in time. We take advantage of this property of the wavelet analysis in order to examine the temporal variation of the period of the umbral oscillations using ground-based observations of the solar atmosphere. We use this real-life signal in order to test the capabilities of different wavelets and to see the problems that arise in analyzing such a signal. We use the continuous wavelet transform in order to perform the analysis and the \"a/spl grave/ trous\" algorithm as a detrending tool.","PeriodicalId":351073,"journal":{"name":"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131662315","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 : 2002-11-07DOI: 10.1109/ICDSP.2002.1028172
Shouhong Zhu, Pushpakanthan Arasaratnam, A. Constantinides
This paper addresses the problem of stochastic approximation and data re-use applied to the blind adaptive algorithm for the interference cancellation RAKE CDMA receiver. The improved adaptive algorithm that utilizes step-size adaptation can achieve both faster convergence and higher steady state performance compared to the fixed step-size ones without increasing much more complexity. Moreover, the improved adaptive algorithm that further utilizes solution averaging and data re-use can further improve both convergence speed and steady state performance. Simulations support the resulting significant improvements.
{"title":"Stochastic approximation and data re-use applied to blind adaptive algorithm for interference cancellation RAKE CDMA receiver","authors":"Shouhong Zhu, Pushpakanthan Arasaratnam, A. Constantinides","doi":"10.1109/ICDSP.2002.1028172","DOIUrl":"https://doi.org/10.1109/ICDSP.2002.1028172","url":null,"abstract":"This paper addresses the problem of stochastic approximation and data re-use applied to the blind adaptive algorithm for the interference cancellation RAKE CDMA receiver. The improved adaptive algorithm that utilizes step-size adaptation can achieve both faster convergence and higher steady state performance compared to the fixed step-size ones without increasing much more complexity. Moreover, the improved adaptive algorithm that further utilizes solution averaging and data re-use can further improve both convergence speed and steady state performance. Simulations support the resulting significant improvements.","PeriodicalId":351073,"journal":{"name":"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132657080","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 : 2002-11-07DOI: 10.1109/ICDSP.2002.1028327
S. Haar, R. Zukunft, F. Vogelbruch
In this paper a timing recovery criterion is derived from the optimum feedforward coefficients of an adaptive symbol-spaced complex-valued decision feedback equalizer (DFE). The criterion is deduced by evaluating the relationship of sampling phase and corresponding, in the minimum mean square error (MMSE) sense optimum, equalizer tap weights exemplarily for a typical digital subscriber line (DSL) scenario. It turns out that a linear combination of the real and imaginary parts of the precursor and cursor coefficient can be applied as timing recovery criterion suitable for digital implementation.
{"title":"A timing recovery criterion derived from the tap weights of a decision feedback equalizer for QAM digital subscriber line systems","authors":"S. Haar, R. Zukunft, F. Vogelbruch","doi":"10.1109/ICDSP.2002.1028327","DOIUrl":"https://doi.org/10.1109/ICDSP.2002.1028327","url":null,"abstract":"In this paper a timing recovery criterion is derived from the optimum feedforward coefficients of an adaptive symbol-spaced complex-valued decision feedback equalizer (DFE). The criterion is deduced by evaluating the relationship of sampling phase and corresponding, in the minimum mean square error (MMSE) sense optimum, equalizer tap weights exemplarily for a typical digital subscriber line (DSL) scenario. It turns out that a linear combination of the real and imaginary parts of the precursor and cursor coefficient can be applied as timing recovery criterion suitable for digital implementation.","PeriodicalId":351073,"journal":{"name":"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133334584","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 : 2002-11-07DOI: 10.1109/ICDSP.2002.1028255
Nicholas Evans, J. Mason, Benoit G. B. Fauve
This paper addresses the problem of noise estimation for speech enhancement and automatic speech recognition. In the context of mobile telephony, there is a requirement for low resource algorithms which must run at real-time. This paper describes the implementation of a previously published approach, termed quantile-based noise estimation, integrated within a conventional spectral subtraction framework. The novelty lies in the efficiency of the noise estimation process. Assessment is carried out on the AURORA corpus and demonstrates significant improvements in efficiency. Automatic speech recognition results show an average relative improvement of 26% over the baseline.
{"title":"Efficient real-time noise estimation without explicit speech, non-speech detection: an assessment on the AURORA corpus","authors":"Nicholas Evans, J. Mason, Benoit G. B. Fauve","doi":"10.1109/ICDSP.2002.1028255","DOIUrl":"https://doi.org/10.1109/ICDSP.2002.1028255","url":null,"abstract":"This paper addresses the problem of noise estimation for speech enhancement and automatic speech recognition. In the context of mobile telephony, there is a requirement for low resource algorithms which must run at real-time. This paper describes the implementation of a previously published approach, termed quantile-based noise estimation, integrated within a conventional spectral subtraction framework. The novelty lies in the efficiency of the noise estimation process. Assessment is carried out on the AURORA corpus and demonstrates significant improvements in efficiency. Automatic speech recognition results show an average relative improvement of 26% over the baseline.","PeriodicalId":351073,"journal":{"name":"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132791331","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 : 2002-11-07DOI: 10.1109/ICDSP.2002.1028299
P. Spyridonos, D. Glotsos, D. Cavouras, P. Ravazoula, G. Nikiforidis
In this paper our purpose was to design a prognostic-classification system, based on a probabilistic neural network (PNN), for predicting urine bladder cancer recurrence. Ninety-two patients with bladder cancer were diagnosed and followed up. Images from each patient tissue sample were digitized and an adequate number of nuclei per case were segmented for the generation of morphological and textural nuclear features. Automatic urine bladder tumor characterization as a potential to recur or not was performed utilizing a PNN. An exhaustive search based on classifier performance indicated the best feature combination that produced the minimum classification error. The classification performance of the PNN was optimized employing a 4-dimensional feature vector that comprised one texture feature and three descriptors of nucleus size distribution. The classification accuracy for the group of cases with recurrence was 72.3% (35/47) and 71.1% (32/45) accuracy for the group of cases with no recurrence. The proposed prognostic-system could prove of value in rendering the diagnostic nuclear information a marker of disease recurrence.
{"title":"A prognostic-classification system based on a probabilistic NN for predicting urine bladder cancer recurrence","authors":"P. Spyridonos, D. Glotsos, D. Cavouras, P. Ravazoula, G. Nikiforidis","doi":"10.1109/ICDSP.2002.1028299","DOIUrl":"https://doi.org/10.1109/ICDSP.2002.1028299","url":null,"abstract":"In this paper our purpose was to design a prognostic-classification system, based on a probabilistic neural network (PNN), for predicting urine bladder cancer recurrence. Ninety-two patients with bladder cancer were diagnosed and followed up. Images from each patient tissue sample were digitized and an adequate number of nuclei per case were segmented for the generation of morphological and textural nuclear features. Automatic urine bladder tumor characterization as a potential to recur or not was performed utilizing a PNN. An exhaustive search based on classifier performance indicated the best feature combination that produced the minimum classification error. The classification performance of the PNN was optimized employing a 4-dimensional feature vector that comprised one texture feature and three descriptors of nucleus size distribution. The classification accuracy for the group of cases with recurrence was 72.3% (35/47) and 71.1% (32/45) accuracy for the group of cases with no recurrence. The proposed prognostic-system could prove of value in rendering the diagnostic nuclear information a marker of disease recurrence.","PeriodicalId":351073,"journal":{"name":"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114137243","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 : 2002-11-07DOI: 10.1109/ICDSP.2002.1028199
J. Chao
It is shown that adaptive training of quadratic Volterra filters is an ill-conditioned problem, or the error surfaces of the adaptive filters (ADF) are always extremely steep in one particular direction but relatively flat in the rest of the directions. This result is a generalization of a previous report on the special case of when the inputs are delayed values of a single time series of Gaussian distribution. A complete analysis of the correlation matrix of inputs as multiple time series are also obtained for the unrelated case. This paper then presents a fast RLS algorithm for Gaussian input signals costing only O(N/sup 2/) multiplications where N is the number of linear terms in the filter input, the same order as the LMS algorithm, while the RLS algorithm for Volterra ADF costs O(N/sup 5/) multiplications per sample. Simulations shown that this algorithm works well also in non-Gaussian input cases.
{"title":"Analysis and fast RLS algorithms of quadratic Volterra ADF","authors":"J. Chao","doi":"10.1109/ICDSP.2002.1028199","DOIUrl":"https://doi.org/10.1109/ICDSP.2002.1028199","url":null,"abstract":"It is shown that adaptive training of quadratic Volterra filters is an ill-conditioned problem, or the error surfaces of the adaptive filters (ADF) are always extremely steep in one particular direction but relatively flat in the rest of the directions. This result is a generalization of a previous report on the special case of when the inputs are delayed values of a single time series of Gaussian distribution. A complete analysis of the correlation matrix of inputs as multiple time series are also obtained for the unrelated case. This paper then presents a fast RLS algorithm for Gaussian input signals costing only O(N/sup 2/) multiplications where N is the number of linear terms in the filter input, the same order as the LMS algorithm, while the RLS algorithm for Volterra ADF costs O(N/sup 5/) multiplications per sample. Simulations shown that this algorithm works well also in non-Gaussian input cases.","PeriodicalId":351073,"journal":{"name":"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116435497","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：