Image and Video Compression: Fundamentals, Applications, and Standards A 4-Day Intensive Course For more information, please see our WWW homepage at http://www.ee.pdx.edu/short_courses/image_compression/ Seats are very limited, early registration is encouraged! About the course Recent years have witnessed a surge in the need for storage and transmission of digital images and video. Digital cameras and scanners have proliferated the use of digital images in various consumer and commercial applications. Digital broadcast systems and digital video on CD-ROM, which can be played back by affordable multimedia-enabled PC's, have made digital video part of everyday life. Despite the increases in storage and transmission capacities, efficient storage and transmission of images and video is still the foremost challenge. Thus, image and video compression plays a key enabling role for almost all consumer, commercial, and scientific applications. Digital image and video compression is a current focus of research and international standardization. Recent standards such as JPEG, JBIG, H.261, H.263, MPEG-1 and MPEG-2, and the emerging standards such as MPEG-4, reflect the state-of-the-art algorithms, and are important in facilitating interoperability among various imaging systems and wide-spread, cost-effective deployment of the technology. Emerging technologies such as wavelets have shown promise in replacing some of the current standards as they might provide more functionality than is available from today's standards. The course provides a detailed description of the fundamentals, a working knowledge of the various image and video compression standards, and a technical description of the emerging technologies. Upon completion of the course, students will be equipped with the background in information theory that will help them understand the performance limitations of various compression solutions. Further, they will gain a solid understanding of the basic principles and standards of digital image and video compression in such a way as to optimize their use for a particular application. Finally, they will gain a technical understanding of the emerging technologies, such as wavelets and fractals, that will enable them to assess their value in serving niche markets not addressed by the current standards, as well as their impact on the development of future standards. The course starts on the first day with a broad set of product and application examples that establish the need for compression. This is followed by a brief description of the existing and emerging image and video compression standardization activities, their scope and their functionalities. Next, the three main components of compression systems, representation, quantization, and symbol modeling and encoding are discussed. The topic of symbol modeling and encoding is studied in detail where fundamental concepts, such as Markov models, entropy, and Shannon's noiseless coding theorem, are discussed. A working knowledge of various encoding strategies, such as Huffman coding, arithmetic coding, LZW coding, and Rice coding, is presented and their relative merits and shortcomings are compared. Finally, lossless encoding algorithms, such as the current and emerging JPEG lossless standard and bit plane/JBIG coding, are explained. The second day focuses on lossy image compression and the JPEG standard. It also builds the foundation for video compression schemes such as the MPEG and the H.26x family of standards. First, a brief review of various quantization strategies, such as scalar, vector, and trellis-coded quantization, is provided and their performance merits are compared. This is followed by a detailed description of transform coding with particular emphasis on the discrete cosine transform (DCT), the fundamental building block of all image and video compression standards. Next, the JPEG international standard for the compression of continuous-tone color still images is studied and its baseline, extended, and enhanced modes of operation are described in detail. Various issues regarding the implementation of JPEG in practical systems, such as the design of Q tables, the effect of multiple coding and software and hardware speed, are discussed. Numerous image examples supplement the technical descriptions. The third day deals with emerging technologies and video compression. Wavelet and sub-band encoding schemes and their performance merits relative to DCT are studied both analytically and by subjective evaluation of many image examples. The basics of fractal image compression are reviewed. Video compression, and the major components of a video compression system, pre-processing, encoding, decoding, and post-processing, are discussed. Fundamental principles of motion estimation and an overview of widely used motion estimation algorithms, such as block matching and hierarchical block matching, are presented. Motion estimation utilizes the temporal redundancies in video sequences to increase compression efficiency. It also facilitates the development of multi-frame pre- and post-processing algorithms that are more powerful than their single-frame counterparts. Principles and algorithms of motion-compensated noise suppression and defect removal are presented as examples of pre-processing. Pre-processing is often among the differentiating factors used in evaluation of an entire video compression system due to its significant impact on the resulting compression efficiency. Video format standards conversion is an important post-processing step, especially in multimedia applications where the decoded video may have to be displayed by a system adhering to a different video format standard. Techniques for interlace-to-progressive scan conversion and frame rate conversion are discussed and the importance of motion information in standards conversion is demonstrated. Finally, a detailed discussion of the fundamentals and the working principles of the MPEG1 video compression standard is provided. The final day is devoted to MPEG2, MPEG4, H.261 and H.263 standards. The MPEG2 video compression standard is presented with emphasis on its differences from MPEG1. Its applications in digital video disk (DVD) and Advanced TV (ATV) standardization are also discussed. An overview of the emerging MPEG4 standard is presented which targets new application areas with increased interactivity and extendibility. The second half of this day is devoted to video conferencing standards beginning with H.261 which targets ISDN at data rates of multiples of 64 k-bits/sec. The newly developed standard, H.263, incorporates several recent innovations over H.261 and targets data rates less than 64 k-bits/sec. It has demonstrated acceptable quality over PST-N networks using 28.8 k-bit/sec modems and promises to bring video conferencing to the mass consumer market. Details of H.261 and H.263 will be presented, followed by demonstrations of video quality using simulations and product demos. Instructors: Majid Rabbani, Eastman Kodak Company M. Ibrahim Sezan, Sharp Laboratories of America Thomas Gardos, Intel Corporation Organizers: Fu Li Rolf Schaumann Portland State University Course Outline Introduction -- Need for compression (application and product examples.) -- Statistical redundancy and perceptual irrelevancy, examples -- Compression building blocks transformation, quantization, symbol modeling and encoding -- Brief overview of lossless and lossy compression standards Symbol Modeling and Encoding -- Markov modeling and entropy -- Huffman coding -- Arithmetic coding -- Rice coding -- LZW coding Lossless Compression Techniques -- Differential Pulse Code Modulation (DPCM) -- Bit plane encoding and JBIG -- Current and emerging JPEG lossless standards Quantization Strategies -- Uniform scalar -- Nonuniform MM-SE scalar (Lloyd-Max) -- Entropy constrained quantization (ECQ) -- Vector quantization (VQ) -- Trellis-coded quantization (TCQ) The JPEG International Standard" 2n -- Discrete cosine transform (DCT) -- Baseline JPEG -- Extended JPEG features -- Enhancements to JPEG (adaptive quantization for fixed-rate JPEG, etc.) -- JPEG implementation issues (fast DCT's, effect of multiple coding, design of quantization tables, etc.) Emerging Technologies -- Wavelets (analysis and synthesis filter design, quantization and coding strategies, comparisons to JPEG, etc.) -- Fractals (Jacquin's technique, weighted finite automata (WFA)) Motion Estimation -- Overview of widely used algorithms (block matching, hierarchical block matching) Pre-and Post-Processing -- Motion-compensated noise filtering as pre-processing -- Video format conversion: interlace to proscan and frame rate conversion. Video Compression Standards -- The MPEG1 standard -- The MPEG2 standard (including discussions on rate control, bit-stream syntax and utilization in Digital Video Disk and Advanced TV standardization). -- The H.261 and H.263 standards. Examples of silicon and board- level implementations of standards. -- Actual product demonstrations About the Instructors MAJID RABBANI - received his Ph.D. degree in electrical engineering from the UW-Madison in 1983. He is currently a Research Associate and the head of the image compression and video processing group in the Imaging Science Division of Eastman Kodak Research Laboratories. He is also involved in many educational activities among which are teaching graduate courses at Rochester Institute of Technology (RIT), satellite courses for NTU (National Technological University), and short course for SPIE, IS&T, SID, and other technical Societies. He is the recipient of the 1988 C. E. K. Mees Award (Kodak's highest award for for excellence in research) and the co-recipient of the 1990 Emmy Engineering Award in recognition of the Kodak Still-Video Transceiver System. He represents Kodak at the International JPEG and MPEG organizations. Dr. Rabbani has testified as an expert witness for the digital processing of images and video in several court cases, including the digital enhancement of the Rodney King beating videotape in 1993. His current research interests span the various aspects of digital signal and image processing where he has published over 40 technical articles and holds 11 patents. He is a fellow of SPIE and a senior member of IEEE. He also was the general Symposium Chair for the 1996 SPIE/IS&T co-sponsored Electronic Imaging Symposium in San Jose. He is the coauthor of the book ``Digital Image Compression Techniques'' published in 1991, the editor of the SPIE Milestone Series on "Image Coding and Compression", published in 1992. IBRAHIM SEZAN - received his Ph.D degree in Electrical, Computer and Systems Engineering from Rensselaer Polytechnic Institute in 1984. He is currently the Senior Manager of Digital Video Processing at Sharp Laboratories of America, Camas, Washington. He also holds an adjunct Associate Professor position at the Electrical Engineering Department at the University of Rochester. From 1984 to 1996, he worked at Eastman Kodak Company, Rochester, New York, where he headed the Motion and Video Technology Area in the Imaging Research and Advanced Development Laboratories from 1992 to 1996. Dr. Sezan was the co-recipient of the A. B. Du Mont award at Rensselaer Polytechnic Institute in 1984. During 1988-1992, he served as an Associate Editor of the IEEE Transactions on Medical Imaging. From 1992 to 1994, he was an Associate Editor of the IEEE Transactions on Image Processing. He contributed to the books Image Recovery: Theory and Application (Academic Press, 1987), Mathematics in Signal Processing (Oxford, 1987), Handbook of Signal Processing (Marcell Dekker, 1988), Digital Image Restoration (Springer Verlag, 1991), Real-Time Optical Information Processing (Academic Press, 1994), and edited Selected Papers in Digital Image Restoration (SPIE Milestone Series, 1992). He is the co-editor of the book Motion Analysis and Image Sequence Processing, published by Kluwer in 1993. His current research interests include video modeling, analysis and processing, and their applications to video compression and digital video databases. Dr. Sezan is a participant in the MPEG standards; he actively publishes and teaches in the area of image and video processing. THOMAS GARDOS - received his Ph.D. in electrical engineering from the Georgia Institute of Technology in Atlanta, Georgia in 1993. He is currently senior engineer in the Intel Architecture Labs of Intel Corporation where he is technical lead on development of standards-based and propriety video compression algorithms for video conferencing applications. He represents Intel at the ITU H.263 standards group and is principal representative to ISO's MPEG4 group. He chairs the audio/video compression subcommittee of the Intel Research Council which is the formal channel of interaction to academia at Intel. He also is an adjunct instructor at Portland State University and Oregon State University where he teaches courses on digital image and video processing. He has served as Image Processing conference and session chairs at the SPIE Electronic Imaging Symposia in San Jose. He won the Best Student Paper award at SPIE's 1992 Visual Communications Conference and was awarded an NSF Fellowship in the 1991 Japan Summer Institute. His current interests are in image and video compression as well as multidimensional signal processing where he has authored numerous articles and patent applications. Registration Information Dates: Monday, August 5 - Thursday, August 8, 1996 Times: Regular sessions will begin at 8:30 AM and end at 5:00 PM. Refreshments will be served at 8:00 AM daily and at breaks. Lunch periods will be from 12:00 to 1:30. Location: Classes will be held at Portland State University, (PSU), located in downtown Portland. Detailed information will be sent to registrants. For further information: Phone: (503) 725-3806 or 1-800-547-8887 ext. 3806 Email: laura@ee.pdx.edu WWW: http://www.ee.pdx.edu/short.course/image_compression/ Early Registration: $1195. Registration form and payment must be postmarked JULY 10, 1996\fR. Late Registration: $1295. Registration form and payment postmarked AFTER JULY 10, 1996. All registration materials must be received JULY 25, 1996. Fees include lecture, course materials, refreshments and a Certificate of Completion. A 15% discount will be granted when 6 or more people from the same company location register for the course. Refund: A full refund will be given for cancelations received at PSU by mail, phone, or e.mail, prior to July 25, 1996. NO REFUND will be made for a cancelation notice received after July 25, 1996, or for no attendance. A substitute may attend in place of the registered participant. Accommodations: For reservations made by July 15, 1996, special rates for participants have been arranged with: Airline-Carlson Travel: 1-800-634-2306, 5% Airline discount (Credit Cards Only). Ask for Catherine. Days Inn City Center: 1-800-899-0248, $64 single and double occupancy Red Lion Inn, Portland Center: (503) 221-0450, $105 single, $120 double Mention Video and Image Compression when making reservations. Both hotels are a pleasant 10 minute walk to PSU. Buses and MAX trains in the downtown area are free, so it should not be necessary to rent a car. Other nearby hotels: The Benson:(503)228-2000 Heathman Hotel:(503)241-4100 Hilton Hotel:(503)226-1611 Mallory Hotel:(503)223-6311 Marriott Hotel:(503)226-7600 Excursions: Spousal/Companion activities will be arranged depending on interest. Intensive Course Registration Image and Video Compression: Fundamentals, Applications, and Standards August 5 - 8, 1996 Portland State University, Portland, Oregon _____________________________________________ Name _____________________________________________ Company _____________________________________________ Address _____________________________________________ City/State/Zip _____________________________________________ Work Phone Email address Payment Options: $1195 if postmarked BY July 10, 1996 $1015 per person for six or more registrations from one company location. $1295 if postmarked AFTER July 10, 1996 $1100 per person for six or more registrations from one company location. Enclosed is a check made payable to Portland State University - Electrical Engineering Department Please charge the registration fee to my credit card: Visa __________ MasterCard __________ ____________________________________________ Account Number, Expiration Date ____________________________________________ Signature I would like to receive information on the Spousal/Companion activities. MAIL OR FAX FORM TO: Portland State University Department of Electrical Engineering Image and Video Compression P.O. Box 751 Portland, OR 97207-0751 Phone: (503) 725-3806 Fax: (503) 725-3807 Email: laura@ee.pdx.edu All registration materials must be received by July 25, 1996 For more information, please see our WWW homepage at http://www.ee.pdx.edu/short_courses/image_compression/ Please Post ************************************* Please Forward