Paulo V. K. Borges. Flat 1, 50A, Cephas Av. London, UK, E1 4AR (+44) PRESENTATION

Transcription

1 Paulo V. K. Borges Flat 1, 50A, Cephas Av. London, UK, E1 4AR (+44) PRESENTATION Electronic engineer working as researcher at University of London. Doctorate in digital image/video processing, with strong focus on statistical signal processing methods. Experience with digital watermarking and multimedia authentication, consisting of embedding and retrieval of hidden data in noisy signals. Currently working with video event detection, applied for data retrieval. Experienced with algorithm implementation using C++ and Matlab. Strong list of publications in top quality signal processing literature. Also interested in general signal processing, pattern recognition and stochastic processes applied to finance. WORK EXPERIENCE Sept 2007 to Present Signal Processing Research Engineer working for Queen Mary, University of London, UK. Representing Queen Mary, University of London in Mesh Project (European Union Integrated Project). Team management supervising staff in project related work. Developer of signal detection algorithms for identifying patterns in video signals, providing results as stand-alone applications developed in C++ (for integration with other project partners in other institutions). Use of fundamentals of detection and estimation theory, stochastic process analysis and general signal and image processing (space-frequency transforms) for successful identification of specific events in random image scenarios (e.g. automated detection of fire in surveillance cameras, detection of specific types of content in news cast content, among others). Researcher developing new algorithms for signal event detection, successfully publishing scientific papers in international journals and conferences. Assistant lecturer in Image Processing Methods and Visual Programming (using Matlab), for undergraduate students from Queen Mary, University of London. Dec 2006 to Sept 2007 Ph.D Research Student with Queen Mary, University of London, UK. Research on digital watermarking algorithms, for the embedding and detection of hidden data in printed documents. Distinct fields of study in engineering were addressed, as the proposed solution involves several disciplines such as fundamentals of probability and statistics, statistical signal and image processing, and communications. Specifically, research time has been devoted to scanning noise, halftoning, pattern recognition and classification methods, higher order

2 statistics, information coding, noise models and fundamental aspects of detection theory. Analysis of statistical feature extraction in the frequency domain, using Fourier and wavelet based analysis. Financial support from CNPq SWE Scholarship, an extremely competitive grant provided by the Brazilian government for research abroad. Mar 2004 to Nov 2006 Ph.D Research Student with Federal University of Santa Catarina, Brazil. Work on authentication methods for hardcopy document security. Main goal of the research was to transmit and detect data after distortions caused by the print and scan process, which corrupts data causing non-linear distortions, filtering, and addition of correlated and non-correlated noise. Noise modeling and characterization from real physical distortions. Development of signal detection algorithm using object oriented C++, using higher order statistics. Assistant lecturer in Control and Signal Processing, Level II, for undergraduate students. Mar 2002 to Mar 2004 M.Sc. Research Student with Federal University of Santa Catarina, Brazil. Development of digital watermarking methods for still images, using innovative approach for transmission and detection of hidden signals based on the position of patterns in the signal. Development of correlation based methods for signal detection in noisy environments, using perceptual models and optimization theory for optimal detection. Analysis of statistical correlation performance in the frequency domain, using Fourier and wavelet based analysis. Teaching: Lecturer in the course Introduction to Digital Image Processing, in IX CIPEEL, Cycle of Courses in Electrical Engineering, in the Technology Center, UFSC. July 2001 to Dec 2001 Researcher and developer working for University of Manchester (Institute of Science and Technology), UK. Designing and testing a video processing algorithm for video enhancement in noisy conditions (foggy weather and underwater video). Main goal was to eliminate the distortion noise and extract only desired signal. Study and understanding of inverse filtering techniques for image enhancement. Real field test mounting video equipment on airplane model and transmitting data to ground for real time processing.

3 July 1998 to June 2001 Scientific Initiation researcher working for the Department of Informatics and Statistics, Federal University of Santa Catarina, Brazil. Granted a research scholarship from CNPq (Brazil National Research Funding Agency). EDUCATION Mar 2004 to Dec 2007 Intermediate level study of programming languages C, C++. Development of computer applications (database, web sites) for several events, including the III Neural Networks Brazilian Congress and the IV Brazilian Neural Networks Workshop, in July, Research on Artificial Intelligence (AI) methods. Application of C++ in software related to AI (specially Sugal, a platform for implementation of genetic algorithms). Ph.D in Electronic Engineering - Federal University of Santa Catarina, Brazil and Queen Mary University of London, UK. Thesis Title: Text Luminance Modulation for Hardcopy Watermarking. Mar 2002 to Mar 2004 M.Sc. in Electronic Engineering - Federal University of Santa Catarina, Brazil. Thesis Title: Positional Model for Digital Watermarking Systems. Mar 1997 to Dec 2001 B.S. in Electrical Engineering - Federal University of Santa Catarina, Brazil. Area Subject: Information Technology, Communications and Signal Processing. First two years ( ) dedicated to advanced mathematics and physics foundation courses. June 1996 High School Diploma from Palmetto Senior High School, Miami, FL, USA. COMPUTER SKILLS Programming Languages and Systems Programming Languages: C++, Matlab. Intermediate knowledge of Php, MySql, HTML and Flash. Linux / Windows user. Latex user.

4 PUBLICATIONS Journals Paulo V. K. Borges, Joceli Mayer and Ebroul Izquierdo, Robust and transparent color modulation for text data hiding, accepted for publication in IEEE Transactions on Multimedia, Paulo V. K. Borges, Joceli Mayer and Ebroul Izquierdo, Document image processing for paper side communications, accepted for publication in IEEE Transactions on Multimedia, Paulo V. K. Borges and Joceli Mayer, Text luminance modulation for hardcopy watermarking, Signal Processing, Elsevier, Vol. 87, Issue 7, July Paulo V. K. Borges and Joceli Mayer, Analysis of position based watermarking, Springer-Verlag Pattern Analysis and Applications, PAA Magazine, p. 1-12, Paulo V. K. Borges and Joceli Mayer, Improving position based watermarking and its application in the wavelet domain, Hifen Magazine - Brazilian Computer Society. October, Conferences Paulo V. K. Borges, Joceli Mayer and Ebroul Izquierdo, Efficient visual fire detection applied for video retrieval, accepted to 16th EURASIP European Signal Processing Conference, EUSIPCO 2008, Lausanne, Switzerland, September Paulo V. K. Borges, Joceli Mayer and Ebroul Izquierdo, A probabilistic model for flood detection in video sequences, accepted to IEEE International Conference on Image Processing, ICIP 2008, San Diego, CA, USA, October Paulo V. K. Borges, Joceli Mayer and Ebroul Izquierdo, Efficient text color modulation for printed side communications and data hiding, accepted to IEEE proceedings of XXI Brazilian Symposium on Computer Graphics and Image Processing, SIBGRAPI 2008, Campo Grande, Brazil, October Paulo V. K. Borges, Joceli Mayer and Ebroul Izquierdo, Performance analysis of text halftone modulation, IEEE International Conference on Image Processing, ICIP 2007, San Antonio, Texas, USA, September Paulo V. K. Borges, Joceli Mayer and Ebroul Izquierdo, Segmentation of document images using higher order statistics, IEEE International Workshop on Multimedia Signal Processing, MMSP 2007, Chania, Greece, October Paulo V. K. Borges, Joceli Mayer and Ebroul Izquierdo, Efficient side information encoding for text hardcopy documents, accepted for IEEE International Conference on Advanced Video and Signal Based Surveillance AVSS 2007, London, UK, September Paulo V. K. Borges, Joceli Mayer and Ebroul Izquierdo, A practical protocol for digital and printed document authentication, 15th EURASIP European Signal Processing Conference, EUSIPCO 2007, Poznan, Poland, September Paulo V. K. Borges and Joceli Mayer, Improving robustness in printed side communications using higher order statistics, IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP - Hawaii, USA, April, 2007.

5 Paulo V. K. Borges and Joceli Mayer, Document watermarking via character luminance modulation, in IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP - Toulouse, France, May, Paulo V. K. Borges, Robinson Pizzio and Joceli Mayer, Image watermarking for document authentication, SBSEG - Brazilian Symposium on Information Security, Florianpolis, Brazil, Paulo V. K. Borges and Joceli Mayer, Positional embedding for multibit watermarking, in IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP - Philadelphia, USA, Paulo V. K. Borges and Joceli Mayer, Informed position based watermarking, in IEEE Proceedings of SIBGRAPI-SIAGC - Brazilian Symposium on Computer Graphics and Image Processing and Ibero-American Symposium on Computer Graphics, Curitiba, Brazil, October Paulo V. K. Borges and Joceli Mayer, Position based watermarking, in IEEE Proceedings of the 3rd International Conference on Image and Signal Processing and Analysis - ISPA Conference. Rome, Italy, September Paulo V. K. Borges e Joceli Mayer, Position based watermarking applied in DCT domain, no III Simpsio Catarinense de Processamento Digital de Imagens - Florianpolis, SC, Brasil, Outubro de LANGUAGE SKILLS Main Languages Reading Speaking Writing Understanding English Fluent Fluent Fluent Fluent French Good Regular Regular Regular Spanish Good Good Regular Regular Portuguese Native Native Native Native ADDITIONAL INFORMATION Memberships and Awards IEEE (Institute of Electrical and Electronic Engineers) member since Money awarded participant for best presentation at UKIVA (United Kingdom Industrial Vision Association) Workshop - Recent Advances in Camera Technology for Machine Vision. (September, 2001, Manchester, UK). Courses Participant at IFEW (International Finance and Enterprize Week), fair and conference, in Manchester, UK Course: Harmonics in Industrial Power Systems, promoted by the Department of Electrical Engineering, at the University Federal de Santa Catarina, May Course: Introduction to Matlab, promoted by the Department of Industrial Engineering, at the Federal University of Santa Catarina Course: Introduction to Neural Networks by Dr. Bernard Widrow, at the III Brazilian Conference on Neural Networks, July Course: Genetic Algorithms, at the III Brazilian Conference on Neural Networks -July, 1997.

6 Mini-course: Neural Networks, at the IV Brazilian Workshop on Neural Networks, July 1997;