{"title":"Estimation of n-mode ranks of hyperspectral images for tensor denoising","authors":"Damien Letexier, S. Bourennane","doi":"10.5281/ZENODO.41785","DOIUrl":"https://doi.org/10.5281/ZENODO.41785","url":null,"abstract":"This paper deals with n-mode subspaces in tensor based denoising. Actually, the main issue of tensor signal processing is the estimation of n-mode ranks since a subspace based approach is considered. In hyperspectral images, an efficient denoising method could allow more accurate results for classification or unmixing. In this paper, we propose to extend subspace identification methods to tensors for n-mode rank estimation. The estimation of endmembers in hyperspectral images is equivalent to estimate the 3-mode rank of a tensor. HySime and Neyman-Pearson detection theory-based thresholding method (HFC) are practical benchmarks. Therefore, we adopt tensor formalism to extend reference algorithms to determine n-mode ranks of tensors. We compare different adapted criteria both on simulated and real data.","PeriodicalId":106989,"journal":{"name":"2009 17th European Signal Processing Conference","volume":"1994 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128638125","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}
{"title":"Multi Library Wavelet Neural Networks for 3D face recognition using 3D facial shape representation","authors":"W. B. Soltana, W. Bellil, C. Amar, A. Alimi","doi":"10.5281/ZENODO.41296","DOIUrl":"https://doi.org/10.5281/ZENODO.41296","url":null,"abstract":"This paper presents a new approach for 3D face modeling and recognition. Motivated by finding a representation that embodies a high power of discrimination between face classes, a new type of 3D shape descriptors is suggested. We have developed a fully automatic system which uses an alignment algorithm to register 3D facial scans. In addition, scalability in both time and space is achieved by converting 3D facial scans into compact wavelet metadata. Our system consists in two phases. The first phase is called enrolment composed of 3 steps: data processing, alignment and metadata generating. The metadata generating step is powered by the use of Multi Library Wavelet Neural Networks (MLWNN). The second phase is called Authentication it starts with the calculation of depth distances between a probe and gallery 3D face. A K-Nearest Neighbors (K-NN) technique is used for 3D face classification. The results of this contribution are more interesting, in comparison with some others works, in term of recognition rate using the GavabDB 3D facial database.","PeriodicalId":106989,"journal":{"name":"2009 17th European Signal Processing Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129889262","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}
N. Johnson, J. Thompson, S. McLaughlin, Francisco J. Garcia
{"title":"A comparison of some bottleneck-link detection methods for network tomography","authors":"N. Johnson, J. Thompson, S. McLaughlin, Francisco J. Garcia","doi":"10.5281/ZENODO.41635","DOIUrl":"https://doi.org/10.5281/ZENODO.41635","url":null,"abstract":"Network tomography offers a useful method to identify internal problems in a network using data which can be obtained at the network's edge. Provided the topology of the network is known then it is possible to recover from the edge measurements some properties of internal links of the network which may not be accessible for any number of reasons - cost, ownership, physical location etc. In this paper we introduce two new estimation algorithms based on the Pearson type-1 distribution and compare these with existing estimator and detector algorithms used to find the bottleneck link in a wired network, that is, the link experiencing the highest delay.","PeriodicalId":106989,"journal":{"name":"2009 17th European Signal Processing Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130858718","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}
{"title":"Objective evaluation of feedback reduction techniques in hearing aids","authors":"A. Spriet, M. Moonen, J. Wouters","doi":"10.5281/ZENODO.41558","DOIUrl":"https://doi.org/10.5281/ZENODO.41558","url":null,"abstract":"This paper proposes an objective evaluation of feedback reduction techniques in four commercial hearing aids and one recent feedback cancellation algorithm. The added stable gain was determined for a speech and a music signal in two acoustic conditions. In addition, the reduction of feedback and oscillations at gain values below the maximum stable gain was measured. Added stable gains between 1 dB and 21 dB were found. Most feedback cancellers achieve worse feedback suppression for the music signal than for the speech signal. Constraining the feedback canceller based on an initial feedback path measurement improves the performance for music signals at the expense of a worse feedback suppression in the acoustic conditions that differ from the condition for which the initialization was performed.","PeriodicalId":106989,"journal":{"name":"2009 17th European Signal Processing Conference","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130347379","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}
{"title":"Interpolation-based calibration for near-field source localization","authors":"Hongyang He, Yide Wang, J. Saillard","doi":"10.5281/ZENODO.41677","DOIUrl":"https://doi.org/10.5281/ZENODO.41677","url":null,"abstract":"In this paper, we present an interpolation-based method for near-field array calibration. Based on an analysis of the received signal model, the position-dependent errors are modeled by a correction matrix. By interpolating the correction matrix, pseudo calibration data can be obtained numerically. The proposed method allows us to calibrate the array responses on a dense grid by taking a small number of measurements. It is shown via simulations that this method has a good performance in near-filed array calibration.","PeriodicalId":106989,"journal":{"name":"2009 17th European Signal Processing Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130592503","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}
{"title":"Filter banks for hearing aids applying subband amplification: A comparison of different specification and design approaches","authors":"D. Alfsmann, H. Göckler, Thomas Kurbiel","doi":"10.5281/ZENODO.41454","DOIUrl":"https://doi.org/10.5281/ZENODO.41454","url":null,"abstract":"Hearing instruments employ filter bank systems (FBS) to subdivide the microphone signal into subband signals. To reduce overall computation, decimation is applied, which inevitably induces disturbance. First, these effects are analysed in detail. Then, we postulate application specific FBS requirements in view of extensive subband signal amplification. Next, we compare four different prototype filter specification and design approaches for oversampling complex-modulated FBS with respect to the postulated requirements. Finally, we present design examples applying these approaches. Thus, we explicitly demonstrate the impact of subband signal amplification on the FBS characteristics.","PeriodicalId":106989,"journal":{"name":"2009 17th European Signal Processing Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128772732","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}
{"title":"Synthetic aperture signal processing for high resolution 3D image reconstruction in the THz-domain","authors":"M. Vandewal, R. Heremans, M. Acheroy","doi":"10.5281/ZENODO.41524","DOIUrl":"https://doi.org/10.5281/ZENODO.41524","url":null,"abstract":"The purpose of this paper is to demonstrate the application of synthetic aperture imaging used in radar and sonar to the terahertz (THz) domain and to create high resolution three-dimensional images. For this demonstration the paper presents images - based on simulated data - which reveal the performance to be expected of synthetic aperture imaging for different frequencies in the THz band. The processed target responses of pulsed broadband radiation show high resolution which can lead to an improvement of non-destructive defect identification.","PeriodicalId":106989,"journal":{"name":"2009 17th European Signal Processing Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128928620","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}
I. Shafi, J. Ahmad, Syed Ismail Shah, F. M. Kashif
{"title":"Quantitative evaluation of concentrated time-frequency distributions","authors":"I. Shafi, J. Ahmad, Syed Ismail Shah, F. M. Kashif","doi":"10.5281/ZENODO.41483","DOIUrl":"https://doi.org/10.5281/ZENODO.41483","url":null,"abstract":"This work objectively evaluates and presents a quantitative analysis of concentrated time-frequency distributions (TFDs) obtained through Network of Expert Neural Networks (NENNs). The objective methods include the ratio of norms based measures, Shannon & Rényi entropy measures, normalized Rényi entropy measure and Jubisa measure. The introduction of these measures allows quantifying the quality of TFDs instead of relying solely on visual inspection of their plots. Performance comparison with various other quadratic TFDs is provided too.","PeriodicalId":106989,"journal":{"name":"2009 17th European Signal Processing Conference","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126769191","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}
S. Bonettini, F. Benvenuto, R. Zanella, L. Zanni, M. Bertero
{"title":"Gradient projection approaches for optimization problems in image deblurring and denoising","authors":"S. Bonettini, F. Benvenuto, R. Zanella, L. Zanni, M. Bertero","doi":"10.5281/ZENODO.41603","DOIUrl":"https://doi.org/10.5281/ZENODO.41603","url":null,"abstract":"Gradient type methods are widely used approaches for nonlinear programming in image processing, due to their simplicity, low memory requirement and ability to provide medium-accurate solutions without excessive computational costs. In this work we discuss some improved gradient projection-methods for constrained optimization problems in image deblurring and denoising. Crucial feature of these approaches is the combination of special steplength rules and scaled gradient directions, appropriately designed to achieve a better convergence rate. Convergence results are given by exploiting monotone or nonmonotone line-search strategies along the feasible direction. The effectiveness of the algorithms is evaluated on the problems arising from the maximum likelihood approach to the deconvolution of images and from the edge-preserving removal of Poisson noise. Numerical results obtained by facing large scale problems involving images of several mega-pixels on graphics processors are also reported.","PeriodicalId":106989,"journal":{"name":"2009 17th European Signal Processing Conference","volume":"240 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114067641","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}
{"title":"Genetic algorithm-aided fixed-point design of E-UTRA PRACH detector on multi-core DSP","authors":"Rongrong Qian, Tao Peng, Yuan Qi, Wenbo Wang","doi":"10.5281/ZENODO.41297","DOIUrl":"https://doi.org/10.5281/ZENODO.41297","url":null,"abstract":"This paper presents a new genetic algorithm (GA)-aided methodology of software implementation in Digital Signal Processors (DSPs) under both the computational accuracy and bus bandwidth constraints. The design issue is firstly stated as two classes of fixed-point design problems, one of which is then formulated to a constrained integer programming (CIP) problem. And the genetic algorithm is proposed to treat with such CIP problem for the sake of efficiency. Then the fixed-point evolved (E)-UTRA PRACH detector is presented, which further underlines the feasibility and convenience of applying this methodology to practice. Finally, the numeric results justify the proposed GA-aided approach and demonstrate that a speedup by a factor of 33 can be achieved compared to the exhaustive search for the solution of E-UTRA PRACH detector design problem.","PeriodicalId":106989,"journal":{"name":"2009 17th European Signal Processing Conference","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114146875","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}