Visual information retrieval (VIR) is an active and vibrant research area, which attempts at providing means for organizing, indexing, annotating, and retrieving visual information (images and videos) from large, unstructured repositories. The goal of VIR is to retrieve matches ranked by their relevance to a given query, which is often expressed as an example image and/or a series of keywords. During its early years (1995-2000), the research efforts were dominated by content-based approaches contributed primarily by the image and video processing community. During the past decade, it was widely recognized that the challenges imposed by the lack of coincidence between an image's visual contents and its semantic interpretation, also known as semantic gap, required a clever use of textual metadata (in addition to information extracted from the image's pixel contents) to make image and video retrieval solutions efficient and effective. The need to bridge (or at least narrow) the semantic gap has been one of the driving forces behind current VIR research. Additionally, other related research problems and market opportunities have started to emerge, offering a broad range of exciting problems for computer scientists and engineers to work on. In this introductory book, we focus on a subset of VIR problems where the media consists of images, and the indexing and retrieval methods are based on the pixel contents of those images -- an approach known as content-based image retrieval (CBIR). We present an implementation-oriented overview of CBIR concepts, techniques, algorithms, and figures of merit. Most chapters are supported by examples written in Java, using Lucene (an open-source Java-based indexing and search implementation) and LIRE (Lucene Image REtrieval), an open-source Java-based library for CBIR.

The research in content-based indexing and retrieval of visual information such as images and video has become one of the most populated directions in the vast area of information technologies. Social networks such as YouTube, Facebook, FileMobile, and DailyMotion host and supply facilities for accessing a tremendous amount of professional and user generated data. The areas of societal activity, such as, video protection and security, also generate thousands and thousands of terabytes of visual content. This book presents the most recent results and important trends in visual information indexing and retrieval. It is intended for young researchers, as well as, professionals looking for an algorithmic solution to a problem.

Readings in Multimedia Computing and Networking captures the broad areas of research and developments in this burgeoning field, distills the key findings, and makes them accessible to professionals, researchers, and students alike. For the first time, the most influential and innovative papers on these topics are presented in a cohesive form, giving shape to the diverse area of multimedia computing. The seminal moments are recorded by a dozen visionaries in the field and each contributing editor provides a context for their area of research by way of a thoughtful, focused chapter introduction. The volume editors, Kevin Jeffay and HongJiang Zhang, offer further incisive interpretations of past and present developments in this area, including those within media and content processing, operating systems, and networking support for multimedia. This book will provide you with a sound understanding of the theoretical and practical issues at work in the field's continuing evolution. * Offers an in-depth look at the technical challenges in multimedia and provides real and potential solutions that promise to expand the role of multimedia in business, entertainment, and education.* Examines in Part One issues at the heart of multimedia processes: the means by which multimedia data are coded, compressed, indexed, retrieved, and otherwise manipulated.* Examines in Part Two the accommodation of these processes by storage systems, operating systems, network protocols, and applications.* Written by leading researchers, the introductions give shape to a field that is continually defining itself and place the key research findings in context to those who need to understand the state-of-the art developments.

Intelligent Image Databases: Towards Advanced Image Retrieval addresses the image feature selection issue in developing content-based image retrieval systems. The book first discusses the four important issues in developing a complete content-based image retrieval system, and then demonstrates that image feature selection has significant impact on the remaining issues of system design. Next, it presents an in-depth literature survey on typical image features explored by contemporary content-based image retrieval systems for image matching and retrieval purposes. The goal of the survey is to determine the characteristics and the effectiveness of individual features, so as to establish guidelines for future development of content-based image retrieval systems. Intelligent Image Databases: Towards Advanced Image Retrieval describes the Advanced Region-Based Image Retrieval System (ARBIRS) developed by the authors for color images of real-world scenes. They have selected image regions for building ARBIRS as the literature survey suggests that prominent image regions, along with their associated features, provide a higher probability for achieving a higher level content-based image retrieval system. A major challenge in building a region-based image retrieval system is that prominent regions are rather difficult to capture in an accurate and error-free condition, particularly those in images of real-world scenes. To meet this challenge, the book proposes an integrated approach to tackle the problem via feature capturing, feature indexing, and database query. Through comprehensive system evaluation, it is demonstrated how these systematically integrated efforts work effectively to accomplish advanced image retrieval. Intelligent Image Databases: Towards Advanced Image Retrieval serves as an excellent reference and may be used as a text for advanced courses on the topic.

Exploration of Visual Data presents latest research efforts in the area of content-based exploration of image and video data. The main objective is to bridge the semantic gap between high-level concepts in the human mind and low-level features extractable by the machines. The two key issues emphasized are "content-awareness" and "user-in-the-loop". The authors provide a comprehensive review on algorithms for visual feature extraction based on color, texture, shape, and structure, and techniques for incorporating such information to aid browsing, exploration, search, and streaming of image and video data. They also discuss issues related to the mixed use of textual and low-level visual features to facilitate more effective access of multimedia data. Exploration of Visual Data provides state-of-the-art materials on the topics of content-based description of visual data, content-based low-bitrate video streaming, and latest asymmetric and nonlinear relevance feedback algorithms, which to date are unpublished.

Visual information retrieval (VIR) is an active and vibrant research area, which attempts at providing means for organizing, indexing, annotating, and retrieving visual information (images and videos) from large, unstructured repositories. The goal of VIR is to retrieve matches ranked by their relevance to a given query, which is often expressed as an example image and/or a series of keywords. During its early years (1995-2000), the research efforts were dominated by content-based approaches contributed primarily by the image and video processing community. During the past decade, it was widely recognized that the challenges imposed by the lack of coincidence between an image's visual contents and its semantic interpretation, also known as semantic gap, required a clever use of textual metadata (in addition to information extracted from the image's pixel contents) to make image and video retrieval solutions efficient and effective. The need to bridge (or at least narrow) the semantic gap has been one of the driving forces behind current VIR research. Additionally, other related research problems and market opportunities have started to emerge, offering a broad range of exciting problems for computer scientists and engineers to work on. In this introductory book, we focus on a subset of VIR problems where the media consists of images, and the indexing and retrieval methods are based on the pixel contents of those images -- an approach known as content-based image retrieval (CBIR). We present an implementation-oriented overview of CBIR concepts, techniques, algorithms, and figures of merit. Most chapters are supported by examples written in Java, using Lucene (an open-source Java-based indexing and search implementation) and LIRE (Lucene Image REtrieval), an open-source Java-based library for CBIR. Table of Contents: Introduction / Information Retrieval: Selected Concepts and Techniques / Visual Features / Indexing Visual Features / LIRE: An Extensible Java CBIR Library / Concluding Remarks