IBM Multimedia Analysis and Retrieval System

Overview

Requirements

Download

FAQs

Forum

Reviews

Update: June 2, 2008

What is IBM Multimedia Analysis and Retrieval System?

IBM® Multimedia Analysis and Retrieval System is an automated content indexing and multimodal search system for digital image and video collections. This system addresses the problem of indexing, classifying, and searching large volumes of images and videos: It can visually analyze images and videos, categorize them based on appearance and associated metadata, and make them more searchable than they are when only associated text metadata are used.

Existing solutions require the user to describe visual content manually. Manual tagging is time-consuming and often subjective, leading to incomplete and inconsistent annotations of images and video and thus preventing efficient cataloging of the current deluge of multimedia data. IBM Multimedia Analysis and Retrieval System is unique in its approach to analyzing and fusing audio, visual, and text information in order to automatically annotate multimedia data.

This tool is being developed at IBM Research.

How does it work?

IBM Multimedia Analysis and Retrieval System automatically indexes unlabeled images and videos repositories with a set of classifiers, using machine learning approaches.

IBM Multimedia Analysis and Retrieval System provides a number of important multimedia browsing and search functions in its dynamic search interface that are based on content (such as color, texture, shape, and edges), content clusters, models (such as scenes, objects, and events), and text (such as speech, closed captions, textual metadata, and user-associated tags). Users can query image and video repositories using concept models, visual feature descriptors, and extracted metadata as needed for a particular query. Users can tag individual video shots or meaningful groups of shots created from the fused multi-modal index.