Aymen Bougacha, J. Boughariou, M. Slima, A. Hamida, K. Mahfoudh, O. Kammoun, C. Mhiri
{"title":"Comparative study of supervised and unsupervised classification methods: Application to automatic MRI glioma brain tumors segmentation","authors":"Aymen Bougacha, J. Boughariou, M. Slima, A. Hamida, K. Mahfoudh, O. Kammoun, C. Mhiri","doi":"10.1109/ATSIP.2018.8364463","DOIUrl":"https://doi.org/10.1109/ATSIP.2018.8364463","url":null,"abstract":"MRI is a noninvasive neuro-imaging modality largely used in neurology explorations and provides more objective and valuable diagnostic information for High-grade gliomas (HGG). In this context, HGG Segmentation is challenging due to their heterogeneous nature. The present research investigates a comparative study of supervised and unsupervised classification methods for MRI glioma segmentation. These methods are tested with data sets defined in BRATS 2015. We noted that artificial neural networks (ANN) provide efficient segmentation results based on DICE and Jaccard evaluation metrics.","PeriodicalId":332253,"journal":{"name":"2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131336285","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}
Nouha Jaoua, P. Vanheeghe, Nicolas Navarro, Olivier Langlois, Marius Iordache
{"title":"A Bayesian approach for parameter estimation in railway systems","authors":"Nouha Jaoua, P. Vanheeghe, Nicolas Navarro, Olivier Langlois, Marius Iordache","doi":"10.1109/ATSIP.2018.8364485","DOIUrl":"https://doi.org/10.1109/ATSIP.2018.8364485","url":null,"abstract":"In this paper, we address the problem of parameter estimation in railway systems. For this purpose, a physical model of the train based on the fundamental principle of dynamics is proposed. Then, the parameter estimation is handled via an approach using a combination of Expectation-Maximization algorithm and Sequential Monte Carlo methods. The experiments performed both on synthetic and real data show the efficiency of the considered method.","PeriodicalId":332253,"journal":{"name":"2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128850850","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":"Microstrip and HMSIW six-port junctions designs and comparison","authors":"S. Lakhdhar, F. Harabi, A. Gharsallah","doi":"10.1109/ATSIP.2018.8364521","DOIUrl":"https://doi.org/10.1109/ATSIP.2018.8364521","url":null,"abstract":"In this paper, micro-strip, SIW and HMSIW couplers operating at a center frequency of 2.45 GHz were presented and compared. Simulations of the three couplers were presented over a frequency band from 1.8 GHz to 3.2 GHz. Compared to the micro-strip coupler, the SIW one is characterized by low lost and high Q value but it suffers from the big size in low frequency band, So to realize a nearly 50% reduction in size with keeping the good performances of the SIW technology, half mode substrate integrated wave guide HMSIW origins from SIW has been used. A novel structure of a six-port junction based on HMSIW technology was designed with a low cost FR4 substrate and compared to a conventional six-port junction based on micro-strip technology. Good performances were achieved with our proposed HMSIW six-port junction.","PeriodicalId":332253,"journal":{"name":"2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134263820","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":"Analysis of descriptors relevant to image search by content","authors":"Amira Slimani, Z. Lachiri","doi":"10.1109/ATSIP.2018.8364452","DOIUrl":"https://doi.org/10.1109/ATSIP.2018.8364452","url":null,"abstract":"This article investigates the relevance of visual descriptors in content based search. We propose an approach of indexing and searching of images by content based on the extraction of different vectors characteristic of remote sensing images decomposed into wavelets [6]. It is shown that the Coiflets-3 have better performances in terms of results and computation time for images with a strong directional predominance. It is shown that the Daubechies-3 and Symmlet-3 wavelets show better results on asymmetric or random images. The results of this work are compared with previous work and show a clear improvement.","PeriodicalId":332253,"journal":{"name":"2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134618785","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":"Land change detection using multivariate alteration detection and Chi squared test thresholding","authors":"A. Tahraoui, R. Khedam, A. Bouakache, A. B. Aissa","doi":"10.1109/ATSIP.2018.8364501","DOIUrl":"https://doi.org/10.1109/ATSIP.2018.8364501","url":null,"abstract":"In this paper we shall describe a statistical approach for land change detection based on multivariate alteration detection (MAD) transformation combined with a thresholding method based on Chi squared test. Unlike the most other multivariate change detection techniques, the MAD analysis is invariant to linear and affine transformations of the input data. Consequently, it is insensitive to linear differences in atmospheric conditions or sensor calibrations of multitemporal acquisitions. Detected change objects by the MAD variates are then extracted by means of the studied thresholding technique. We proposed also post-processing of the change detected using the MAD variates by means of maximum autocorrelation factor (MAF) analysis. A case study with SPOT-HRV multispectral data before and after a flood event occurred in November 2000 shows the usefulness of the proposed MAD/Chi-2 and MAF/MAD/Chi-2 change detection schemes according to the ground truth of the study zone.","PeriodicalId":332253,"journal":{"name":"2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128703528","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 and practical swarm optimisation algorithms for patient-specific seizure detection systems","authors":"S. Ammar, Omar Trigui, Senouci Mohamed","doi":"10.1109/ATSIP.2018.8364465","DOIUrl":"https://doi.org/10.1109/ATSIP.2018.8364465","url":null,"abstract":"The automatic seizure detection system is designed to aid the physician's decision-making process with recognizing the sought EEG segments. Increasing the system sensitivity is the goal of several studies. In fact, ameliorating this criterion allows to find the same interpretations as found with a visual scanning. A patient-specific system is able to set its optimal parameters according to the patient which makes it more accurate than non-patient-specific system. This paper introduces a new patient-specific system with genetic and practical swarm optimisation algorithms. The results show that the proposed system is able to reach acceptable performances. Moreover, the use of the genetic algorithm improves the system sensitivity (95%) more than the practical swarm optimization (91%) which makes it a better method for the system parameter optimisation.","PeriodicalId":332253,"journal":{"name":"2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130485338","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}
Bilel Ameur, M. Belahcene, Sabeur Masmoudi, A. Hamida
{"title":"Weighted PCA-EFMNet: A deep learning network for Face Verification in the Wild","authors":"Bilel Ameur, M. Belahcene, Sabeur Masmoudi, A. Hamida","doi":"10.1109/ATSIP.2018.8364460","DOIUrl":"https://doi.org/10.1109/ATSIP.2018.8364460","url":null,"abstract":"The term “Wild” refers to unconstrained face recognition considered as a challenging problem due to considerable intra-class variations resulting from lighting, occlusion, facial expressions and poses changes. These challenges greatly influence the facial recognition systems performance, especially those relying on 2D information. The paper proposes an efficient deep learning network for feature extraction based on data processing components: 1) Cascaded Weighted principal component analysis with enhanced fisher model (WPCA-EFM); 2) Binary hashing; and 3) Histograms. Weighted PCA-EFM, our proposed architecture, was applied in order to learn multistage filter banks. Then, simple block histograms and simple binary hashing were applied for indexing and pooling. Therefore, the proposed architecture, named the Weighted PCA-EFM network (Weighted PCA-EFMNet), can be efficiently and easily designed and learned for Face Verification in the Wild. Ultimately, the classification is carried employing distance measure Cosine as well as support vector machine (SVM). Our experiments were carried out on real-world dataset: Labeled Faces in the Wild (LFW). Experimental results show that the proposed methods achieve high accuracy of 95%.","PeriodicalId":332253,"journal":{"name":"2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131010075","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":"Robust watermarking scheme integrated into JPWL based on Turbo-Trellis-Coded quantization","authors":"Hanen Rhayma, A. Makhloufi, A. Hmida","doi":"10.1109/ATSIP.2018.8364456","DOIUrl":"https://doi.org/10.1109/ATSIP.2018.8364456","url":null,"abstract":"The big revolution from analog to digital makes digital documents extremely used due to many advantages such as cheapness and speed diffusion. Nonetheless, this crossing to digital forms is accompanied with a less controllable distribution. As a consequence, the intellectual copyright is no more protected which may cause some economic losses. In this paper, we intend to present a possible solution to solve copyright ownership problem and to verify the originality of content. In this context, we propose to embed a robust watermark at the Wireless JPEG2000 (JPWL) encoder by using Turbo Trellis-Coded Quantization (turbo-TCQ) technique. In particular, Special attention will be given to joint quantification and watermark embedding, simultaneously, during compression. The extraction of the marque is performed during decompression. The experimental results showed that the proposed joint scheme successfully survives lossy compression attacks generated by the encoder JPWL itself with insignificant alteration of the image quality even at high ratio.","PeriodicalId":332253,"journal":{"name":"2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131328060","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}
J. Gastellu-Etchegorry, L. Landier, A. Al Bitar, N. Lauret, T. Yin, Jianbo Qi, J. Guilleux, E. Chavanon, C. Feigenwinter, Z. Mitraka, N. Chrysoulakis
{"title":"Time series of urban radiative budget maps derived from EO satellites using a physical remote sensing model","authors":"J. Gastellu-Etchegorry, L. Landier, A. Al Bitar, N. Lauret, T. Yin, Jianbo Qi, J. Guilleux, E. Chavanon, C. Feigenwinter, Z. Mitraka, N. Chrysoulakis","doi":"10.1109/ATSIP.2018.8364509","DOIUrl":"https://doi.org/10.1109/ATSIP.2018.8364509","url":null,"abstract":"Models that simulate the radiative budget (RB) and remote sensing (RS) observation of landscapes with physical approaches and consideration of the three-dimensional (3-D) architecture of Earth surfaces are increasingly needed to better understand the life-essential cycles and processes of our planet and to further develop RS technology. DART (Discrete Anisotropic Radiative Transfer) is one of the most comprehensive physically based 3-D models of Earth-atmosphere optical radiative transfer (RT), from ultraviolet to thermal infrared. It simulates the optical 3-D RB and signal of proximal, aerial and satellite imaging spectrometers and laser scanners, for any urban and/or natural landscapes and for any experimental and instrumental configurations. It is freely available for research and teaching activities. Here, an application is presented after a summary of its theory and recent advances: inversion of Sentinel 2 images for simulating time series of urban radiative budget QV maps through the determination of maps of urban surface material. Results are very encouraging: satellite and in-situ Qsiv are very close (RMSE » 15 W/m2; i.e. 2.7% mean relative difference).","PeriodicalId":332253,"journal":{"name":"2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116111500","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}
H. Abdelmoula, A. Kallel, J. Roujean, Sihem Châabouni, K. Gargouri, M. Ghrab, J. Gastellu-Etchegorry, N. Lauret
{"title":"Bayesian inversion technique of olive tree biophysical properties using Sentinel-2 images","authors":"H. Abdelmoula, A. Kallel, J. Roujean, Sihem Châabouni, K. Gargouri, M. Ghrab, J. Gastellu-Etchegorry, N. Lauret","doi":"10.1109/ATSIP.2018.8364492","DOIUrl":"https://doi.org/10.1109/ATSIP.2018.8364492","url":null,"abstract":"In this paper, we study the estimation of olive tree biophysical properties driven by Sentinel-2 (S2) image inversion. The latter is based on the forward/backward radiative transfer model (RTM). The forward step is done simulating the DART model on a realistic olive tree mock-up, whereas the backward is done based on a coupling between the Look UP Table (LUT) and the Markov Chain Monte Carlo (MCMC). The parameters Leaf area index (LAI), chlorophyll (Cab) water (Cw) contents and mesophyll structure (N) are therefore derived. Soil reflectance is pre-calculated based on an upscaling of the S2 resolution to 3m using Planet images. Moreover to obtain a significant representation of the local heterogeneity, S2 are upscaled to the 80m resolution. The estimation results are promising.","PeriodicalId":332253,"journal":{"name":"2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129642440","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}