Pub Date : 2018-09-01DOI: 10.23919/EUSIPCO.2018.8553447
Carlos A. Prete Junior, V. Nascimento, C. G. Lopes
Acoustic emission testing is widely used by industry to detect and localize faults in structures, but estimated source positions often show significant bias in real tests as a consequence of Time Difference of Arrival (TDOA) bias. In this work, a model for TDOA bias is developed considering the time of arrival was estimated using the fixed threshold algorithm, as well as theoretical upper and lower bounds for it. In addition, we derive the time of arrival probability distribution function in terms of the noise distribution and acoustic emission waveform for the fixed threshold algorithm, showing that, contrary to usual practice, it in general cannot be well approximated by a Gaussian distribution.
{"title":"Modeling Time of Arrival Probability Distribution and TDOA Bias in Acoustic Emission Testing","authors":"Carlos A. Prete Junior, V. Nascimento, C. G. Lopes","doi":"10.23919/EUSIPCO.2018.8553447","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2018.8553447","url":null,"abstract":"Acoustic emission testing is widely used by industry to detect and localize faults in structures, but estimated source positions often show significant bias in real tests as a consequence of Time Difference of Arrival (TDOA) bias. In this work, a model for TDOA bias is developed considering the time of arrival was estimated using the fixed threshold algorithm, as well as theoretical upper and lower bounds for it. In addition, we derive the time of arrival probability distribution function in terms of the noise distribution and acoustic emission waveform for the fixed threshold algorithm, showing that, contrary to usual practice, it in general cannot be well approximated by a Gaussian distribution.","PeriodicalId":303069,"journal":{"name":"2018 26th European Signal Processing Conference (EUSIPCO)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114474295","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 : 2018-09-01DOI: 10.23919/EUSIPCO.2018.8553562
R. Badeau
In the field of room acoustics, it is well known that reverberation can be characterized statistically in a particular region of the time-frequency domain (after the transition time and above Schroeder's frequency). Since the 1950s, various formulas have been established, focusing on particular aspects of reverberation: exponential decay over time, correlations between frequencies, correlations between sensors at each frequency, and time-frequency distribution. In this paper, we introduce a new stochastic reverberation model, that permits us to retrieve all these well-known results within a common mathematical framework. To the best of our knowledge, this is the first time that such a unification work is presented. The benefits are multiple: several new formulas generalizing the classical results are established, that jointly characterize the spatial, temporal and spectral properties of late reverberation.
{"title":"Unified Stochastic Reverberation Modeling","authors":"R. Badeau","doi":"10.23919/EUSIPCO.2018.8553562","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2018.8553562","url":null,"abstract":"In the field of room acoustics, it is well known that reverberation can be characterized statistically in a particular region of the time-frequency domain (after the transition time and above Schroeder's frequency). Since the 1950s, various formulas have been established, focusing on particular aspects of reverberation: exponential decay over time, correlations between frequencies, correlations between sensors at each frequency, and time-frequency distribution. In this paper, we introduce a new stochastic reverberation model, that permits us to retrieve all these well-known results within a common mathematical framework. To the best of our knowledge, this is the first time that such a unification work is presented. The benefits are multiple: several new formulas generalizing the classical results are established, that jointly characterize the spatial, temporal and spectral properties of late reverberation.","PeriodicalId":303069,"journal":{"name":"2018 26th European Signal Processing Conference (EUSIPCO)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115003437","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 : 2018-09-01DOI: 10.23919/EUSIPCO.2018.8553462
Haoyu Li, S. Derrode, L. Benyoussef, W. Pieczynski
This paper presents a pedestrian navigation algorithm based on a foot-mounted 9 Degree of Freedom (DOF) Inertial Measurement Unit (IMU), which provides tri-axial accelerations, angular rates and magnetics. Most algorithms used worldwide employ Zero Velocity Update (ZUPT) to reduce the tremendous error of integration from acceleration to displacement. The crucial part in ZUPT is to detect stance phase precisely. A cyclic left-to-right style Hidden Markov Model is introduced in this work which is able to appropriately model the periodic nature of signals. Stance detection is then made unsupervised by using a suited learning algorithm. Then orientation estimation is performed independently by a quaternion-based method, a simplified error-state Extended Kalman Filter (EKF) assists trajectory reconstruction in 3D space, neither extra method nor prior knowledge is needed to estimate the height. Experimental results on large free-walking trajectories show that the proposed algorithm can provide more accurate locations, especially in z-axis compared to competitive algorithms, w.r.t. to a ground-truth obtained using OpenStreetMap.
{"title":"Free-Walking 3D Pedestrian Large Trajectory Reconstruction from IMU Sensors","authors":"Haoyu Li, S. Derrode, L. Benyoussef, W. Pieczynski","doi":"10.23919/EUSIPCO.2018.8553462","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2018.8553462","url":null,"abstract":"This paper presents a pedestrian navigation algorithm based on a foot-mounted 9 Degree of Freedom (DOF) Inertial Measurement Unit (IMU), which provides tri-axial accelerations, angular rates and magnetics. Most algorithms used worldwide employ Zero Velocity Update (ZUPT) to reduce the tremendous error of integration from acceleration to displacement. The crucial part in ZUPT is to detect stance phase precisely. A cyclic left-to-right style Hidden Markov Model is introduced in this work which is able to appropriately model the periodic nature of signals. Stance detection is then made unsupervised by using a suited learning algorithm. Then orientation estimation is performed independently by a quaternion-based method, a simplified error-state Extended Kalman Filter (EKF) assists trajectory reconstruction in 3D space, neither extra method nor prior knowledge is needed to estimate the height. Experimental results on large free-walking trajectories show that the proposed algorithm can provide more accurate locations, especially in z-axis compared to competitive algorithms, w.r.t. to a ground-truth obtained using OpenStreetMap.","PeriodicalId":303069,"journal":{"name":"2018 26th European Signal Processing Conference (EUSIPCO)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114635540","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 : 2018-09-01DOI: 10.23919/EUSIPCO.2018.8553425
David Semedo, João Magalhães, Flávio Martins
In this paper we address the task of gender classification on picture sharing social media networks such as Instagram and Flickr. We aim to infer the gender of an user given only a small set of the images shared in its profile. We make the assumption that user's images contain a collection of visual elements that implicitly encode discriminative patterns that allow inferring its gender, in a language independent way. This information can then be used in personalisation and recommendation. Our main hypothesis is that semantic visual features are more adequate for discriminating high-level classes. The gender detection task is formalised as: given an user's profile, represented as a bag of images, we want to infer the gender of the user. Social media profiles can be noisy and contain confounding factors, therefore we classify bags of user-profile‘s images to provide a more robust prediction. Experiments using a dataset from the picture sharing social network Instagram show that the use of multiple images is key to improve detection performance. Moreover, we verify that deep semantic features are more suited for gender detection than low-level image representations. The methods proposed can infer the gender with precision scores higher than 0.825, and the best performing method achieving 0.911 precision.
{"title":"Inferring User Gender from User Generated Visual Content on a Deep Semantic Space","authors":"David Semedo, João Magalhães, Flávio Martins","doi":"10.23919/EUSIPCO.2018.8553425","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2018.8553425","url":null,"abstract":"In this paper we address the task of gender classification on picture sharing social media networks such as Instagram and Flickr. We aim to infer the gender of an user given only a small set of the images shared in its profile. We make the assumption that user's images contain a collection of visual elements that implicitly encode discriminative patterns that allow inferring its gender, in a language independent way. This information can then be used in personalisation and recommendation. Our main hypothesis is that semantic visual features are more adequate for discriminating high-level classes. The gender detection task is formalised as: given an user's profile, represented as a bag of images, we want to infer the gender of the user. Social media profiles can be noisy and contain confounding factors, therefore we classify bags of user-profile‘s images to provide a more robust prediction. Experiments using a dataset from the picture sharing social network Instagram show that the use of multiple images is key to improve detection performance. Moreover, we verify that deep semantic features are more suited for gender detection than low-level image representations. The methods proposed can infer the gender with precision scores higher than 0.825, and the best performing method achieving 0.911 precision.","PeriodicalId":303069,"journal":{"name":"2018 26th European Signal Processing Conference (EUSIPCO)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114728293","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 : 2018-09-01DOI: 10.23919/EUSIPCO.2018.8553146
Spyridoula D. Xenaki, K. Koutroumbas, A. Rontogiannis
In this paper a novel efficient online possibilistic c-means clustering algorithm, called Online Generalized Adaptive Possibilistic C-Means (O-GAPCM), is presented. The algorithm extends the abilities of the Adaptive Possibilistic C-Means (APCM) algorithm, allowing the study of cases where the data form compact and hyper-ellipsoidally shaped clusters in the feature space. In addition, the algorithm performs online processing, that is the data vectors are processed one-by-one and their impact is memorized to suitably defined parameters. It also embodies new procedures for creating new clusters and merging existing ones. Thus, O-GAPCM is able to unravel on its own the number and the actual hyper-ellipsoidal shape of the physical clusters formed by the data. Experimental results verify the effectiveness of O-GAPCM both in terms of accuracy and time efficiency.
{"title":"A Novel Online Generalized Possibilistic Clustering Algorithm for Big Data Processing","authors":"Spyridoula D. Xenaki, K. Koutroumbas, A. Rontogiannis","doi":"10.23919/EUSIPCO.2018.8553146","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2018.8553146","url":null,"abstract":"In this paper a novel efficient online possibilistic c-means clustering algorithm, called Online Generalized Adaptive Possibilistic C-Means (O-GAPCM), is presented. The algorithm extends the abilities of the Adaptive Possibilistic C-Means (APCM) algorithm, allowing the study of cases where the data form compact and hyper-ellipsoidally shaped clusters in the feature space. In addition, the algorithm performs online processing, that is the data vectors are processed one-by-one and their impact is memorized to suitably defined parameters. It also embodies new procedures for creating new clusters and merging existing ones. Thus, O-GAPCM is able to unravel on its own the number and the actual hyper-ellipsoidal shape of the physical clusters formed by the data. Experimental results verify the effectiveness of O-GAPCM both in terms of accuracy and time efficiency.","PeriodicalId":303069,"journal":{"name":"2018 26th European Signal Processing Conference (EUSIPCO)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116247326","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 : 2018-09-01DOI: 10.23919/EUSIPCO.2018.8553610
Hiroyuki Kasai
Nonnegative matrix factorization (NMF) is a powerful tool in data analysis by discovering latent features and part-based patterns from high-dimensional data, and is a special case in which factor matrices have low-rank nonnegative constraints. Applying NMF into huge-size matrices, we specifically address stochastic multiplicative update (MU) rule, which is the most popular, but which has slow convergence property. This present paper introduces a gradient averaging technique of stochastic gradient on the stochastic MU rule, and proposes an accelerated stochastic multiplicative update rule: SAGMU. Extensive computational experiments using both synthetic and real-world datasets demonstrate the effectiveness of SAGMU.
{"title":"Accelerated stochastic multiplicative update with gradient averaging for nonnegative matrix factorizations","authors":"Hiroyuki Kasai","doi":"10.23919/EUSIPCO.2018.8553610","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2018.8553610","url":null,"abstract":"Nonnegative matrix factorization (NMF) is a powerful tool in data analysis by discovering latent features and part-based patterns from high-dimensional data, and is a special case in which factor matrices have low-rank nonnegative constraints. Applying NMF into huge-size matrices, we specifically address stochastic multiplicative update (MU) rule, which is the most popular, but which has slow convergence property. This present paper introduces a gradient averaging technique of stochastic gradient on the stochastic MU rule, and proposes an accelerated stochastic multiplicative update rule: SAGMU. Extensive computational experiments using both synthetic and real-world datasets demonstrate the effectiveness of SAGMU.","PeriodicalId":303069,"journal":{"name":"2018 26th European Signal Processing Conference (EUSIPCO)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122162812","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 : 2018-09-01DOI: 10.23919/EUSIPCO.2018.8553461
Paolo Vecchiotti, E. Principi, S. Squartini, F. Piazza
Detecting the presence of speakers and suitably localize them in indoor environments undoubtedly represent two important tasks in the speech processing community. Several algorithms have been proposed for Voice Activity Detection (VAD) and Speaker LOCalization (SLOC) so far, while their accomplishment by means of a joint integrated model has not received much attention. In particular, no studies focused on cooperative exploitation of VAD and SLOC information by means of machine learning have been conducted, up to the authors' knowledge. That is why the authors propose in this work a data driven approach for joint speech detection and speaker localization, relying on Convolutional Neural Network (CNN) which simultaneously process LogMel and GCC-PHAT Patterns features. The proposed algorithm is compared with a two-stage model composed by the cascade of a neural network (NN) based VAD and an NN based SLOC, discussed in previous authors' contributions. Computer simulations, accomplished against the DIRHA dataset addressing a multi-room acoustic environment, show that the proposed method allows to achieve a remarkable relative reduction of speech activity detection error equal to 33% compared to the original NN based VAD. Moreover, the overall localization accuracy is improved as well, by employing the joint model as speech detector and the standard neural SLOC system in cascade.
{"title":"Deep Neural Networks for Joint Voice Activity Detection and Speaker Localization","authors":"Paolo Vecchiotti, E. Principi, S. Squartini, F. Piazza","doi":"10.23919/EUSIPCO.2018.8553461","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2018.8553461","url":null,"abstract":"Detecting the presence of speakers and suitably localize them in indoor environments undoubtedly represent two important tasks in the speech processing community. Several algorithms have been proposed for Voice Activity Detection (VAD) and Speaker LOCalization (SLOC) so far, while their accomplishment by means of a joint integrated model has not received much attention. In particular, no studies focused on cooperative exploitation of VAD and SLOC information by means of machine learning have been conducted, up to the authors' knowledge. That is why the authors propose in this work a data driven approach for joint speech detection and speaker localization, relying on Convolutional Neural Network (CNN) which simultaneously process LogMel and GCC-PHAT Patterns features. The proposed algorithm is compared with a two-stage model composed by the cascade of a neural network (NN) based VAD and an NN based SLOC, discussed in previous authors' contributions. Computer simulations, accomplished against the DIRHA dataset addressing a multi-room acoustic environment, show that the proposed method allows to achieve a remarkable relative reduction of speech activity detection error equal to 33% compared to the original NN based VAD. Moreover, the overall localization accuracy is improved as well, by employing the joint model as speech detector and the standard neural SLOC system in cascade.","PeriodicalId":303069,"journal":{"name":"2018 26th European Signal Processing Conference (EUSIPCO)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116799688","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 : 2018-09-01DOI: 10.23919/EUSIPCO.2018.8552945
P. Birkholz, Patrick Schmaser, Yi Xu
This paper presents a novel method to estimate the pitch target parameters of the target approximation model (TAM). The TAM allows the compact representation of natural pitch contours on a solid theoretical basis and can be used as an intonation model for text-to-speech synthesis. In contrast to previous approaches, the method proposed here estimates the parameters of all targets jointly, uses 5th-order (instead of 3rd-order) linear systems to model the target approximation process, and uses regularization to avoid unnatural pitch targets. The effect of these features on the modeling error and the target parameter distributions are shown. The proposed method has been made available as the open-source software tool TargetOptimizer.
{"title":"Estimation of Pitch Targets from Speech Signals by Joint Regularized Optimization","authors":"P. Birkholz, Patrick Schmaser, Yi Xu","doi":"10.23919/EUSIPCO.2018.8552945","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2018.8552945","url":null,"abstract":"This paper presents a novel method to estimate the pitch target parameters of the target approximation model (TAM). The TAM allows the compact representation of natural pitch contours on a solid theoretical basis and can be used as an intonation model for text-to-speech synthesis. In contrast to previous approaches, the method proposed here estimates the parameters of all targets jointly, uses 5th-order (instead of 3rd-order) linear systems to model the target approximation process, and uses regularization to avoid unnatural pitch targets. The effect of these features on the modeling error and the target parameter distributions are shown. The proposed method has been made available as the open-source software tool TargetOptimizer.","PeriodicalId":303069,"journal":{"name":"2018 26th European Signal Processing Conference (EUSIPCO)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116844926","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 : 2018-09-01DOI: 10.23919/EUSIPCO.2018.8553445
Sally Ghanem, Ashkan Panahi, H. Krim, R. Kerekes, J. Mattingly
Union of Subspaces (UoS) is a new paradigm for signal modeling and processing, which is capable of identifying more complex trends in data sets than simple linear models. Relying on a bi-sparsity pursuit framework and advanced nonsmooth optimization techniques, the Robust Subspace Recovery (RoSuRe) algorithm was introduced in the recent literature as a reliable and numerically efficient algorithm to unfold unions of subspaces. In this study, we apply RoSuRe to prospect the structure of a data type (e.g. sensed data on vehicle through passive audio and magnetic observations). Applying RoSuRe to the observation data set, we obtain a new representation of the time series, respecting an underlying UoS model. We subsequently employ Spectral Clustering on the new representations of the data set. The classification performance on the dataset shows a considerable improvement compared to direct application of other unsupervised clustering methods.
{"title":"Information Subspace-Based Fusion for Vehicle Classification","authors":"Sally Ghanem, Ashkan Panahi, H. Krim, R. Kerekes, J. Mattingly","doi":"10.23919/EUSIPCO.2018.8553445","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2018.8553445","url":null,"abstract":"Union of Subspaces (UoS) is a new paradigm for signal modeling and processing, which is capable of identifying more complex trends in data sets than simple linear models. Relying on a bi-sparsity pursuit framework and advanced nonsmooth optimization techniques, the Robust Subspace Recovery (RoSuRe) algorithm was introduced in the recent literature as a reliable and numerically efficient algorithm to unfold unions of subspaces. In this study, we apply RoSuRe to prospect the structure of a data type (e.g. sensed data on vehicle through passive audio and magnetic observations). Applying RoSuRe to the observation data set, we obtain a new representation of the time series, respecting an underlying UoS model. We subsequently employ Spectral Clustering on the new representations of the data set. The classification performance on the dataset shows a considerable improvement compared to direct application of other unsupervised clustering methods.","PeriodicalId":303069,"journal":{"name":"2018 26th European Signal Processing Conference (EUSIPCO)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120854058","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 : 2018-09-01DOI: 10.23919/EUSIPCO.2018.8553476
Hamza Cherkaoui, L. Gueddari, C. Lazarus, A. Grigis, F. Poupon, A. Vignaud, S. Farrens, Jean-Luc Starck, P. Ciuciu
Compressed Sensing (CS) has allowed a significant reduction of acquisition times in MRI, especially in the high spatial resolution (e.g., 400 $mu{mathrm{m}}$) context. Nonlinear CS reconstruction usually relies on analysis (e.g., Total Variation) or synthesis (e.g., wavelet) based priors and $ell_{1}$ regularization to promote sparsity in the transform domain. Here, we compare the performance of several orthogonal wavelet transforms with those of tight frames for MR image reconstruction in the CS setting combined with parallel imaging (multiple receiver coil). We show that overcomplete dictionaries such as the fast curvelet transform provide improved image quality as compared to orthogonal transforms. For doing so, we rely on an analysis-based formulation where the underlying $ell_{1}$ regularized criterion is minimized using a primal dual splitting method (e.g., Condat-V $tilde{u}$ algorithm). Validation is performed on ex-vivo baboon brain $T^{*}_{2}$ MRI data collected at 7 Tesla and restrospectively under-sampled using non-Cartesian schemes (radial and Sparkling). We show that multiscale analysis priors based on tight frames instead of orthogonal transforms achieve better image quality (pSNR, SSIM) in particular at low signal-to-noise ratio.
{"title":"Analysis vs Synthesis-based Regularization for Combined Compressed Sensing and Parallel MRI Reconstruction at 7 Tesla","authors":"Hamza Cherkaoui, L. Gueddari, C. Lazarus, A. Grigis, F. Poupon, A. Vignaud, S. Farrens, Jean-Luc Starck, P. Ciuciu","doi":"10.23919/EUSIPCO.2018.8553476","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2018.8553476","url":null,"abstract":"Compressed Sensing (CS) has allowed a significant reduction of acquisition times in MRI, especially in the high spatial resolution (e.g., 400 $mu{mathrm{m}}$) context. Nonlinear CS reconstruction usually relies on analysis (e.g., Total Variation) or synthesis (e.g., wavelet) based priors and $ell_{1}$ regularization to promote sparsity in the transform domain. Here, we compare the performance of several orthogonal wavelet transforms with those of tight frames for MR image reconstruction in the CS setting combined with parallel imaging (multiple receiver coil). We show that overcomplete dictionaries such as the fast curvelet transform provide improved image quality as compared to orthogonal transforms. For doing so, we rely on an analysis-based formulation where the underlying $ell_{1}$ regularized criterion is minimized using a primal dual splitting method (e.g., Condat-V $tilde{u}$ algorithm). Validation is performed on ex-vivo baboon brain $T^{*}_{2}$ MRI data collected at 7 Tesla and restrospectively under-sampled using non-Cartesian schemes (radial and Sparkling). We show that multiscale analysis priors based on tight frames instead of orthogonal transforms achieve better image quality (pSNR, SSIM) in particular at low signal-to-noise ratio.","PeriodicalId":303069,"journal":{"name":"2018 26th European Signal Processing Conference (EUSIPCO)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123935097","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：