Nowadays, more and more digital images are being sent over computer networks. The works presented in this tutorial show how encryption algorithms provide security to medical imagery. The main objective is to guarantee the protection of medical images during transmission, and also once this digital data is archived. The subsequent challenge is to ensure that such coding withstands severe treatment such as compression. When a physician receives a visit from a patient, he often requires a specialist opinion before giving a diagnosis. One possible solution is to send images of the patient, along with a specialist report, over a computer network. Nevertheless, computer networks are complex and espionage is a potential risk. We are therefore faced with a real security problem when sending data. For ethical reasons, medical imagery cannot be sent when such a risk is present, and has to be better protected. Encryption is the best form of protection in cases such as this. Many different techniques for the encryption of text already exist. In this tutorial we will show how essential it is to ensure the security of medical imagery and data. In a first time we will present the standard encryption algorithms and will show, in a second time, how these can be suited to medical imagery.
W. Puech was born in December 1967, in France. He received the diploma of Electrical Engineering from the University of Montpellier, France, in 1991 and the Ph.D. Degree in Signal-Image-Speech from the Polytechnic National Institute of Grenoble, France in 1997. He started his research activities in image processing and computer vision. He served as a Visiting Research Associate to the University of Thessaloniki, Greece. From 1997 to 2000, he had been an Assistant Professor in the University of Toulon, France, with research interests including methods of active contours applied to medical images sequences. Since 2000, he is Associate Professor at the University of Montpellier, France. He works now in the LIRMM Laboratory (Laboratory of Computer Science, Robotic and Microelectronic of Montpellier). His current interests are in the areas of protection of visual data (image, video and 3D object) for safe transfer by combining watermarking, data hiding, compression and cryptography. He has applications on medical images, cultural heritage and video surveillance. He is the head of the ICAR team (Image & Interaction).
The LBP operator is defined as a gray-scale invariant texture measure, derived from a general definition of texture in a local neighborhood. Due to its discriminative power and computational simplicity, the LBP texture operator has become a popular approach in various applications, including visual inspection, image retrieval, remote sensing, biomedical image analysis, motion analysis, environment modelling, and outdoor scene analysis. Recent developments showed that the local binary pattern (LBP) texture method also provides outstanding results in representing and analyzing faces in both still images and video sequences. This tutorial presents an overview of the LBP approach and its applications to face analysis. First the theoretical foundations of the method are presented. An overview of applying LBP to various face analysis related tasks is then given, including face recognition, face detection, facial expression recognition, visual-speech recognition and gender classification. Extensions to non-face related applications will also be presented. Finally, directions for future research will be discussed. This tutorial can be seen as an extension to our previous tutorials given at ICPR 2006 (Local Binary Pattern Approach to Computer Vision) and at SCIA 2005 (Texture analysis with local binary patterns: theory and applications).
Title : The Local Binary Pattern Approach and its Applications to Face Analysis.
Author : Dr. Abdenour Hadid, Machine Vision Group Dept. of Electrical and Information Engineering, University of Oulu, Finland.
e-mail : firstname.lastname@example.org
URL : http://www.ee.oulu.fi/~hadid/
|Abstract: || |
Abdenour Hadid received his Engineer Diploma in Computing from the National Institute of Informatics (INI, Algiers), in 1997 and his Doctor of Technology degree in electrical engineering from the University of Oulu, Finland, in 2005. He was a visiting research follow at the Institute of Automation - Chinese Academy of Science in Spring 2006. Now, he is a senior researcher at the Machine Vision Group, University of Oulu (FINLAND). His research interest includes biometrics and facial image analysis, texture analysis, local binary patterns, manifold learning, human-machine interaction, and mobile applications. He authored several papers in international conferences and journals. He served as a reviewer to several international conferences and journals such as: IEEE Transactions on Pattern Analysis and Machine Intelligence, Pattern Recognition Letters, Pattern Recognition, International Journal of information Visualization etc. He is member of the Pattern Recognition Society of Finland. He gave several invited talks and tutorials in international events such as the tutorials on "Local Binary Patterns in Facial Image Analysis" and on "the Local Binary Pattern Approach to Computer Vision" presented in SCIA 2005 and ICPR 2006 (Hong Kong), respectively.
Multichannel imaging systems provide several observations of the same scene which are often corrupted by additive noise and blurred. In this talk, we are interested both in multicomponent image denoising based on a multiscale representation of the image. We firstly review the most conventional wavelet-based denoising methods. Then, we describe the multivariate statistical approach we adopt in order to exploit the correlations existing between the different wavelet subbands. More precisely, we propose a parametric new estimator that includes, in a unifying framework, many reported denoising methods. The derivation of the optimal parameters is achieved by applying the Stein’s principle in the multivariate case. Experiments performed on multispectral remote sensing images clearly indicate the outperformance of our method with the conventional wavelet techniques.
Title : Multichannel image denoising in the wavelet transform domain.
Authors : Pr. A. Benazza, C. Chaux, J.-C. Pesquet, Ecole Supérieure des Communications de Tunis (SUP’COM), Tunisia.
e-mail : email@example.com
URL : ..............
|Abstract: || |
Amel Benazza-Benyahia received the engineering degree from the Institut National des Télécommunications, Evry, France, in 1988, the Ph. D. degree from the Université Paris-Sud (XI), Paris, France, in 1993 and, the Habilitation Universitaire from SUP’COM Tunis, Tunisia, in 2003. Currently, she is a Professor at the Department of Applied Mathematics, Signal Processing, and Communications, SUP’COM. Since 2006, she is at the head of the Unité de Recherche en Imagerie Satellitaire et ses Applications. Her research interests include multispectral image compression and denoising.
Inspired from biological nervous systems and brain structure, Artificial Neural Networks (ANN) have been, over the recent decades, central sources of inspiration for a large number of original techniques covering a vast field of applications. From a general point of view, ANN could be seen as information processing systems taking advantage from learning and generalization capabilities, making these techniques and the issued systems adaptive. Especially, as a result of their adaptability, ANN represent powerful solutions for image processing, pattern recognition and related problems which became during the last decades central points of an ever-increasing range of real-world and industrial applications. Moreover, these solutions may take advantage from the power issued from the high degree of parallelism provided, on the one hand by image’s parallel nature, and on the other hand, by parallel hardware implementation of ANN. The main goal of this tutorial is to present Artificial Neural Network potential, through main ANN models and based techniques, to solve real world industrial problems dealing with Image processing and pattern recognition fields.
Prof. Kurosh Madani: Received his Ph.D. in Electrical Engineering and Computer Sciences from University PARIS 11 (PARIS-SUD), Orsay, France, in 1990. In 1990, he joined Creteil-Senart Institute of Technology of University PARIS 12 – Val de Marne, Lieusaint, France, where he worked from 1990 to 1998 as asistant professor. In 1995, he received the DHDR Doctor Hab. degree from University PARIS 12 – Val de Marne. Since 1996 he is a permanent member (elected Academician) of International Informatization Academy. In 1997, he was also elected as permanent Academician of International Academy of Technological Cybernetics. Since 1998 he works as Professor in Electrical Engineering of Senart Institute of Technology of University PARIS XII – Val de Marne. From 1992 to 2000 he has been creator and head of DRN (Neural Networks Division) research group. From 2001 to 2004 he has been head of Intelligence in Instrumentation and Systems Laboratory of PARIS 12 – Val de Marne University located at Senart Institute of Technology. Since 2005, he is co-director of SCTIC research group, one of the two research groups of Images, Signals and Intelligent Systems Laboratory (LISSI / EA 3956) of PARIS 12 – Val de Marne University. He has worked on both digital and analog implementation of massively parallel processors arrays for image processing by stochastic relaxation, electro-optical random number generation, and both analog and digital Artificial Neural Networks (ANN) implementation. His current research interests include: large ANN structures behavior modeling and implementation, self-organizing, modular and hybrid neural based information processing systems and their software and hardware implementations, design and implementation of real-time neuro-control, humanoid robotics, collective robotics, neural based fault detection and diagnosis systems.
The goal of this tutorial is to discuss the different biometric recognition algorithms (e.g., face, voice, fingerprint and iris, etc..) and to understand the relative advantages and limitations of different approaches. The tutorial will summarize the state of the art methods and results in biometric recognition. We will also discuss the methods based on multiple biometrics (multi-modal biometric) recognition and show the improved results that could be obtained. Issue related to requirements for different biometrics, different ways to choose o biometrics, techniques used to compare and test different biometrics will also be discussed. MATLAB demonstrations will be used to illustrate the different concepts.
Mohamed Deriche received his BS in Electrical Engineering from the National Polytechnic School of Algeria with first class honors (top student). He then joined the University of Minnesota, USA, where he completed his MS and PhD in 1988, and 1992 respectively. He worked for one year as a Post Doctorate Fellow with the University of Minnesota Radiology Department in the area of MRI. He then joined the Queensland University of Technology, Australia, as a Assistant Professor, Associate Professor, then Reader. He joined, in 2001, King Fahd University of Petroleum and Minerals in Saudi Arabia where he is leading the Signal Processing Group. He was awarded the "Best Electrical Engineering Student" award while at the Polytechnique. He has published over two hundred refereed papers in Journals and conferences and has attracted more than $1 Million in research funds. Dr. Deriche supervised 10 PhD students, 5 MS students and been a member of more than 20 PhD and MS committees. He has also supervised more than 60 BS theses. Dr Deriche chaired the IEEE ISSPA conference in 1999. He acted as technical chairman for a number of conferences including: the IEEE TENCON conference in 1997, WOSSPA 1999, IEEE GCCC 2003, IEEE GCC 2004, and the WCBE Signal processing subconference in 2003. He delivered a tutorial on wavelets at ISSPA 1999 and at the BTE 2004, and ISSPA 2005. He was a recipient of the IEEE third Millennium Medal in 2000. His research interests are multiscale signal processing, wavelets, fractals, spectral estimation, with particular emphasis on Multimedia compression applications and biomedical applications.