Author: Pradeep Atrey
Pradeep Atrey is an Associate Professor at the University of Winnipeg,
Canada. His current research focus is on security and privacy issues in
application areas such as surveillance, social networks, and e-health.
He can be reached at p.atrey@uwinnipeg.ca.
The educational column is part of SIGMM's activities and also found at http://www.sigmm.org/Education
SIGMM Education Column of this issue highlights a new book, titled “Visual Information Retrieval using Java and LIRE,” which gives an introduction to the fields of information retrieval and visual information retrieval and points out selected methods, as well as their use and implementation within Java and more specifically LIRE, a Java CBIR library. The book is authored by Dr. Mathias Lux, from Klagenfurt University, Austria, and Prof. Oge Marques, of Florida Atlantic University, and it is published in the Synthesis Lectures on Information Concepts, Retrieval, and Services by Morgan & Claypool.
The basic motivation for writing this book was the need for a fundamental course book that contained just the necessary knowledge to get students started with content-based image retrieval. The book is based on lectures given by the authors over the last years and has been designed to fulfill that need. It will also provide developers for content-based image solutions with a head start by explaining the most relevant concepts and practical requirements.
The book begins with a short introduction, followed by explanations of information retrieval and retrieval evaluation. Visual features are then explained, and practical problems and common solutions are outlined. Indexing strategies of visual features, including linear search, nearest neighbor search, hashing and bag of visual words, are discussed next, and the use of these strategies with LIRE is shown. Finally, LIRE is described in detail, to allow for employment of the library in various contexts and for extension of the functions provided.
There is also a companion website for the book (http://www.lire-project.net), which gives pointers to additional resources and will be updated with slides, figures, teaching materials and code samples.