A key problem in computer vision is image and video understanding, which can be defined as the task of recognizing objects in the scene and their corresponding relationships and semantics, in addition to identifying the scene category itself. Image understanding technology has numerous applications among which are smart capture devices, intelligent image processing, semantic image search and retrieval, image/video utilization (e.g., ratings on quality, usefulness, etc.), security and surveillance, intelligent asset selection and targeted advertising. This tutorial provides an introduction to the theory and practice of image understanding algorithms by studying the various technologies that serve the three major components of a generalized IU system, namely, feature extraction and selection, machine learning tools used for classification, and datasets and ground truth used for training the classifiers. Following this general development, a few application examples are studied in more detail to gain insight into how these technologies are employed in a practical IU system. Applications include face detection, sky detection, image orientation detection, main subject detection, and content based image retrieval (CBIR). Furthermore, realtime demos including face detection and recognition, CBIR, and automatic zooming and cropping of images based on main-subject detection are provided.

This course discusses some of the advanced algorithms in the field of digital image processing. In particular, it familiarizes the audience with the understanding, design, and implementation of advanced algorithms used in deblurring, contrast enhancement, sharpening, noise reduction, and super-resolution in still images and video. Some of the applications include medical imaging, entertainment imaging, consumer and professional digital still cameras/camcorders, forensic imaging, and surveillance. Many image examples complement the technical descriptions.

The ISO JPEG committee is in the final stages of developing a new still-image compression standard, referred to as the JPEG-2000 that will be issued in 6 parts. JPEG-2000 is based on wavelet compression and provides the potential for numerous advantages over the existing JPEG standard. In this course, practical implementations of the wavelet transform, as applied to image compression (e.g., memory efficient implementations and the lifting scheme, various integer and floating point bi-orthogonal filters for lossless and lossy compression, etc.), and related quantization and coding strategies are discussed. The technical details of the JPEG-2000 Part 1 algorithm and syntax are reviewed extensively and the JPEG-2000 performance is compared to that of the existing DCT-based lossy JPEG standard. The superior features of the JPEG-2000 proposed standard are demonstrated by numerous image examples.

The MPEG family of standards is ubiquitous in almost all applications involving digital motion sequences. Examples include VCD, DVD, digital camcorders, digital still cameras with video mode, HDTV, and satellite television. This course is an introduction to the basic concepts as well as the functionalities of the MPEG family of standards, namely, MPEG1, MPEG2, MPEG4-2, and MPEG4-10, aka H.264 or JVT. It includes a comprehensive description of the technical aspects, scope, performance, and differentiating factors of these standards. Special emphasis is placed on H.264 due to its novel features and its importance in enabling many new applications. Numerous image and video examples complement the technical descriptions.

This course presents the state-of-the-art techniques for digital image and video watermarking for a variety of applications. Topics include public-key encryption systems (e.g. RSA), digital signature and authentication schemes (e.g. DSS), methods for detecting invisible watermarks in an image, and a detailed discussion of robust, fragile, and semi-fragile invisible watermarking techniques in spatial and spectral domains. Emphasis will be placed on practical systems that are currently in products or are feasible for inclusion into products. In addition to many image examples, a live demonstration of watermark generation, embedding and extraction in a printing/scanning application will be provided.

This course introduces the basic concepts and applications of electronic imaging. Attendees are familiarized with the components and technologies of an electronic imaging system, including capture, processing, storage, transmission and output. Image examples complement the descriptions.

This course is an introduction to the basic concepts as well as applications of the rapidly emerging field of digital image processing. It familiarizes the audience with the understanding, design, and implementation of algorithms in the various sub-areas of digital image processing such as image enhancement, image deblurring, image understanding, image security, and image compression. Over 200 image examples complement the technical descriptions.

The MPEG family of standards is ubiquitous in almost all applications involving digital motion sequences. Examples include VCD, DVD, digital camcorders, digital still cameras with video mode, HDTV, movies on demand and satellite television. This course is an introduction to the basic concepts as well as the functionalities of the MPEG family of standards, namely, MPEG1, MPEG2, MPEG4-2 (aka MPEG4 Visual), and MPEG4-10 (aka H.264, AVC or JVT). It includes a comprehensive description of the technical aspects, scope, performance, and differentiating factors of these standards. Special emphasis is placed on H.264 due to its novel features and its importance in enabling many new applications. Numerous image and video examples complement the technical descriptions.

This course discusses some of the advanced algorithms in the field of digital image and video processing. In particular, it familiarizes the audience with the understanding, design, and implementation of advanced algorithms used in contrast enhancement, sharpening, noise reduction, and artifact removal in still images and video. Some of the applications include medical imaging, entertainment imaging, digital cameras and camcorders, digital photofinishing, professional photography, forensic imaging, and astronomical imaging. Numerous image examples and live demonstrations complement the technical descriptions.