Electrical and Computer Engineering Faculty Publications Electrical & Computer Engineering 6-11-2008 Significance of Logic Synthesis in FPGA-Based Design of Image and Signal Processing Systems Mariusz Rawski Warsaw University of Technology, [email protected] Henry Selvaraj University of Nevada, Las Vegas, [email protected] Bogdan J. Falkowski Nanyang Technological University, Singapore Tadeusz Luba Institute of Telecommunications Warsaw Follow this and additional works at: https://digitalscholarship.unlv.edu/ece_fac_articles Part of the Computer Engineering Commons, Electrical and Electronics Commons, Power and Energy Commons, Signal Processing Commons, and the Systems and Communications Commons Repository Citation Rawski, M., Selvaraj, H., Falkowski, B. J., Luba, T. (2008). Significance of Logic Synthesis in FPGA-Based Design of Image and Signal Processing Systems. Pattern Recognition Technologies and Applications: Recent Advances 265-283. Hershey, PA: IGI Global. https://digitalscholarship.unlv.edu/ece_fac_articles/303 This Chapter is protected by copyright and/or related rights. It has been brought to you by Digital Scholarship@UNLV with permission from the rights-holder(s). You are free to use this Chapter in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s) directly, unless additional rights are indicated by a Creative Commons license in the record and/or on the work itself. This Chapter has been accepted for inclusion in Electrical and Computer Engineering Faculty Publications by an authorized administrator of Digital Scholarship@UNLV. For more information, please contact [email protected]. Pattern Recognition Technologies and Applications: Recent Advances Brijesh Verma Central Queensland University, Australia Michael Blumenstein Griffith University, Australia INFORMATION SCIENCE REFERENCE Hershey • New York Acquisitions Editor: Kristin Klinger Development Editor: Kristin Roth Assistant Development Editor: Jessica Thompson Senior Managing Editor: Jennifer Neidig Managing Editor: Jamie Snavely Assistant Managing Editor: Carole Coulson Copy Editor: Sue Vander Hook Typesetter: Sean Woznicki Cover Design: Lisa Tosheff Printed at: Yurchak Printing Inc. Published in the United States of America by Information Science Reference (an imprint of IGI Global) 701 E. Chocolate Avenue, Suite 200 Hershey PA 17033 Tel: 717-533-8845 Fax: 717-533-8661 E-mail: [email protected] Web site: http://www.igi-global.com and in the United Kingdom by Information Science Reference (an imprint of IGI Global) 3 Henrietta Street Covent Garden London WC2E 8LU Tel: 44 20 7240 0856 Fax: 44 20 7379 0609 Web site: http://www.eurospanbookstore.com Copyright © 2008 by IGI Global. All rights reserved. No part of this publication may be reproduced, stored or distributed in any form or by any means, electronic or mechanical, including photocopying, without written permission from the publisher. Product or company names used in this set are for identification purposes only. Inclusion of the names of the products or companies does not indicate a claim of ownership by IGI Global of the trademark or registered trademark. Library of Congress Cataloging-in-Publication Data Pattern recognition technologies and applications : recent advances / Brijesh Verma and Michael Blumenstein, editors. p. cm. Summary: “ This book provides cutting-edge pattern recognition techniques and applications. Written by world-renowned experts in their field, this easy to understand book is a must have for those seeking explanation in topics such as on- and offline handwriting and speech recognition, signature verification, and gender classification”--Provided by publisher. Includes bibliographical references and index. ISBN-13: 978-1-59904-807-9 (hardcover) ISBN-13: 978-1-59904-809-3 (e-book) 1. Pattern perception. 2. Pattern perception--Data processing. I. Verma, Brijesh. II. Blumenstein, Michael. Q327.P383 2008 006.4--dc22 2007037396 British Cataloguing in Publication Data A Cataloguing in Publication record for this book is available from the British Library. All work contributed to this book set is original material. The views expressed in this book are those of the authors, but not necessarily of the publisher. Chapter XII Significance of Logic Synthesis in FPGA-Based Design of Image and Signal Processing Systems Mariusz Rawski Warsaw University of Technology, Poland Henry Selvaraj University of Nevada, USA Bogdan J. Falkowski Nanyang Technological University, Singapore Tadeusz Łuba Warsaw University of Technology, Poland ABSTRACT This chapter, taking FIR filters as an example, presents the discussion on efficiency of different imple- mentation methodologies of DSP algorithms targeting modern FPGA architectures. Nowadays, pro- grammable technology provides the possibility to implement digital systems with the use of specialized embedded DSP blocks. However, this technology gives the designer the possibility to increase efficiency of designed systems by exploitation of parallelisms of implemented algorithms. Moreover, it is possible to apply special techniques, such as distributed arithmetic (DA). Since in this approach, general-pur- pose multipliers are replaced by combinational LUT blocks, it is possible to construct digital filters of very high performance. Additionally, application of the functional decomposition-based method to LUT blocks optimization, and mapping has been investigated. The chapter presents results of the comparison of various design approaches in these areas. Copyright © 2008, IGI Global, distributing in print or electronic forms without written permission of IGI Global is prohibited. Significance of Logic Synthesis inFPGA-Based Design of Image and Signal Processing Systems INTRODUCTION gates, a lot of complex gates that can be gener- ated in (semi-) custom CMOS design, and the The pattern recognition research field aims to field programmable logic families that include design methods that allow recognition of patterns various types of (C)PLDs and FPGAs. The other in data. It has important application in image no less important factors of the success are the analysis, character recognition, speech analysis, automation of the design process and hardware and many others. A pattern recognition system description languages. Modern design tools have is composed of sensors gathering observations enabled us to move beyond putting together digital that have to be classified, a feature extraction part components in a schematic entry package to start that provides specific information from gathered writing code in an HDL specification. However, observation, and a classification mechanism that the opportunities created by modern microelec- classifies observation on the basis of extracted tronic technology are not fully exploited because features. Feature extraction methods are re- of weaknesses in traditional logic design meth- sponsible for reducing the resources required to ods. According to the International Technology describe observation accurately. In the case of Roadmap for Semiconductors (1997), the annual image analysis, character recognition, or speech growth rate in design complexity is equal to 58%, analysis, various digital signal-processing (DSP) while the annual growth rate in productivity is algorithms are used to detect desired features only 21% (Figure 1). This means that the number of digitalized image or speech signal. Efficient of logic gates available in modern devices grows implementation of feature extraction-based DSP faster than the ability to design them meaningfully. methods requires specific hardware solutions. New methods are required to aid design process The commercial success of hardware imple- in a way that possibilities offered by modern mentations of image processing systems is due microelectronics are utilized in the highest pos- in large part to revolutionary development in sible degree. microelectronic technologies. By taking advan- In recent years, digital filtering has been recog- tage of the opportunities provided by modern nized as a primary digital signal processing (DSP) microelectronic technology, we are in a position operation. With advances in technology, digital to build very complex digital circuits and systems filters are rapidly replacing analogue filters, which at relatively low cost. There is a large variety of were implemented with RLC components. Digital logic building blocks that can be exploited. The filters are used to modify attributes of signal in library of elements contains various types of the time or frequency domain through a process Figure 1. Difference in growth of device complexity and productivity Significance of Logic Synthesis inFPGA-Based Design of Image and Signal Processing Systems called linear convolution. Traditionally, digital plication of the DWT requires convolution of the signal filtering algorithms are being implemented signal with the wavelet and scaling functions. Ef- using general-purpose programmable DSP chips. ficient hardware implementation of convolution is Alternatively, for high-performance applications, performed as a finite impulse response (FIR) filter. special-purpose fixed functionDSP chipsets and Two filters are used to evaluate aDWT: a high-pass application-specific integrated circuits (ASICs) and a low-pass filter, with the filter coefficients are used. Typical DSP devices are based on the derived from the wavelet basis function.