{"title":"A quadratic classifier based on multispectral texture features for prostate cancer diagnosis","authors":"M. A. Roula, A. Bouridane, F. Kurugollu, A. Amira","doi":"10.1109/ISSPA.2003.1224809","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224809","url":null,"abstract":"This paper is concerned with the development of an automatic classification system for use in prostate cancer diagnosis. The system aims to detect and classify nuclei textures captured from microscopic samples taken from needle biopsies. The main contribution here is that the analysis is carried out over thirty-three spectral bands instead of using the conventional grey scale or RGB colour spaces. A set of texture and morphological features has been computed for all these spectral bands for use in the discrimination phase. The large vector size has then been reduced to a manageable size by using a principal component analysis. Classification tests have been carried out using quadratic discriminant analysis and have shown that multispectral analysis significantly improves the overall classification performances when compared with the case where multispectral features are not considered.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128974279","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":"On the effect of channel knowledge imperfections at the transmitter on the capacity of MIMO systems","authors":"A. Medles, S. Visuri, D. Slock","doi":"10.1109/ISSPA.2003.1224676","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224676","url":null,"abstract":"For a transmitter that has a perfect knowledge of the MIMO channel, the maximum achievable capacity corresponds to the water-filling solution. In practice, the available knowledge may only be partial due to the time selectivity of the channel, and delay or absence of the feedback from the receiver. However, exploiting the partial knowledge leads to a significant improvement when compared to the capacity without any channel knowledge. In this paper we analyze the MIMO capacity with various types of partial knowledge of the channel under practical frequency flat channel models.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128998074","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":"Speech extraction based on ICA and audio-visual coherence","authors":"D. Sodoyer, Laurent Girin, C. Jutten, J. Schwartz","doi":"10.1109/ISSPA.2003.1224816","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224816","url":null,"abstract":"We present a new approach to the source separation problem for multiple speech signals. Using the extra visual information of the speaker's face, the method aims to extract an acoustic speech signal from other acoustic signals by exploiting its coherence with the speaker's lip movements. We define a statistical model of the joint probability of visual and spectral audio input for quantifying the audio-visual coherence. Then, separation can be achieved by maximising this joint probability. Experiments on additive mixtures of 2, 3 and 5 sources show that the algorithm performs well, and systematically better than the classical BSS algorithm JADE.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129150045","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":"Alignment of 3-D medical data sets based on an efficient optimizer and fast voxel recomputation","authors":"M. Capek, J. Hozman","doi":"10.1109/ISSPA.2003.1224806","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224806","url":null,"abstract":"An efficient volume registration based on global information content is described. In a nutshell this task represents an optimization problem that is solved with respect to robustness and computational speed especially. Strong attention is paid to the choice of a function that measures the quality of the registration (mutual information) and to the choice of an optimization strategy that searches for a global optimum of the function in a parametric space (adaptive simulated annealing). To speed the registration procedure a multi-resolution strategy and an incremental approach to volume resampling are used.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"288 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124577824","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":"Full reference and reduced reference metrics for image quality assessment","authors":"M. Carnec, P. Callet, D. Barba","doi":"10.1109/ISSPA.2003.1224743","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224743","url":null,"abstract":"In this paper, we propose efficient full reference and reduced reference image quality assessment metrics. These two metrics are based on human visual system properties to get the best correspondence with human judgments. The full reference metric is generic (independent from image distortion type) and convenient for image coding schemes comparison. From this metric, we have derived a reduced reference metric suitable for quality of service monitoring in a broadcasting purpose. The two metrics share common processings. The main difference between them comes from the selection of information in order to get a high-level representation of images for a reduced reference metric. If limited to a specific type of image coding scheme, the two metrics achieve similar performances.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"6 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127000053","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":"Design of symmetric bi-orthogonal double density wavelet filter banks","authors":"A. Jayawardena","doi":"10.1109/ISSPA.2003.1224915","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224915","url":null,"abstract":"We look at the design of a class of oversampled filter banks and the resulting framelets. The oversampled property is achieved via an extra subband resulting in double density filter banks (DDFB's). We design a class of such filters with linear phase property. We look at a special class of framelets from a filter bank perspective, in that we design double density filter banks (DDFB's). We define type 1 polyphase representation as X (z) = /spl Sigma//sub k=0//sup 1/ z/sup -k/X/sub k/(z/sup 2/) and type 2 polyphase representation as X (z) = /spl Sigma//sub k=0//sup 1/ z/sup k/X/sub k/(z/sup 2/). Polyphase matrices are given in the article, where H/spl tilde/(z) is the type 1 analysis polyphase matrix, and H(z) is the type 2 synthesis polyphase matrix, we can write the perfect reconstruction condition as [H(z)]/sup T/ H/spl tilde/(z) = I.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123525650","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}
A. Benedetto, F. Benedetto, M. D. Blasiis, G. Giunta
{"title":"Ground penetrating radar signal processing for road monitoring and damage detection","authors":"A. Benedetto, F. Benedetto, M. D. Blasiis, G. Giunta","doi":"10.1109/ISSPA.2003.1224706","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224706","url":null,"abstract":"Ground penetrating radar (GPR) signal processing is a nondestructive technique, particularly promising for soil characteristics interpretation. In fact, pavement damage is actually one of the most crucial problems in roads. A preliminary detection and a subsequent classification of the pavement damage, based on an automatic GPR analysis, have been performed and experimentally validated. An optimum detection procedure is performed. It implements the classical Neyman-Pearson radar test. All the settings needed by the procedure have been estimated from a training set of measures. The overall performance has been evaluated by looking at the usual receiver's operating curve. The results evidence that a reasonable performance has been achieved by a suited analysis of GPR images exploiting the spatio-temporal correlation properties of the received signal. Although a generalization is not reliable, this study shows that an automatic GPR-based evaluation of subgrade soil characteristics is feasible.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123670071","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":"Clipping error resilience for peak power-constrained DMT transmission via implicit frequency domain redundancy","authors":"J. Kliewer, T. Karp","doi":"10.1109/ISSPA.2003.1224893","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224893","url":null,"abstract":"In this paper we present a new error correction approach for a simple peak-to-average power ratio (PAR) reduction scheme for discrete multi-tone (DMT) systems based on coefficient clipping. The proposed method utilizes existing or intentionally placed redundancy in the frequency domain in the form of unused subcarriers. Compared to existing PAR reduction algorithms, all signal processing is performed at the receiver after the transmit signal has been simply clipped to a desired maximum amplitude at the front end of the transmitter. The introduced frequency-domain redundancy allows to consider each output vector of the IDFT in the DMT transmitter as codeword of a Bose-Chaudhuri-Hocquenghem (BCH) block code over the field of real numbers. The decoding operation is carried out by a low-complexity linear reconstruction. Simulation results for noisy transmission show that by using the proposed method clipping does not lead to significant errors in the received data if a reasonable amount of redundancy is provided.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121416125","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":"Approximated power iterations for fast subspace tracking","authors":"R. Badeau, G. Richard, B. David, K. Abed-Meraim","doi":"10.1109/ISSPA.2003.1224944","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224944","url":null,"abstract":"This paper introduces a fast implementation of the power iterations method for subspace tracking, based on an approximation less restrictive than the well-known projection approximation. This algorithm guarantees the orthonormality of the estimated subspace-weighting matrix at each iteration, and satisfies a global and exponential convergence property. Moreover, it outperforms many subspace trackers related to the power method, such as PAST. NIC, NP3 and OPAST, while keeping the same computational complexity.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121508894","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":"Source localization with distributed electromagnetic component sensor array processing","authors":"C. See, A. Nehorai","doi":"10.1109/ISSPA.2003.1224669","DOIUrl":"https://doi.org/10.1109/ISSPA.2003.1224669","url":null,"abstract":"We propose an approach to achieve high-performance localisation of multiple sources using a small aperture array of spatially-distributed electric and magnetic component sensors. The approach is based on exploiting of all available electromagnetic information along with the time, delay information. Using simulated data, we demonstrate that this approach outperforms both a single, vector-sensor and scalar-sensor arrays in accuracy of direction-of-arrival (DOA) estimation.","PeriodicalId":264814,"journal":{"name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","volume":"586 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113986345","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}