Warning: this product has no indication of continuing development.(the last release was 2002)
Price: Contact company. Platform: Java toolkit: Windows NT/2000; Mac OS X, Linux, Solaris, SGI IRIX, Oracle. Runs on any JVM-supported environment.
Allows search by similarity to another image, color, shape, texture, and/or object.
Indexes video clips as well as still images.
Built-in functions distill an image or video keyframe to a condensed descriptor called a visual signature which is a vector composed of the calculated values for its four basic properties of color, shape, texture, and object shading/region.
Segments images into objects for searching.
Any type of data that can be represented visually can be indexed and searched, including photographs, illustrations, animation, video and audio.
Can automatically classify images into categories.
Automatically clusters images and allows a representative image to be used to build a "Visual Vocabulary." Can then apply common keywords to all images classified under a Visual Vocabulary cluster in a process called Visual Meta Tagging.
Users can search and retrieve matching images on the Web or as part of an Intranet or asset management system.
Provides automatic generation of visual metadata, proxy, and thumbnails.
Supports flat files and SQL-based database management systems.
Search results can be aggregated from multiple collections; each collection can manage up to 50,000 assets.
Provides multi-threaded support for all services. Utilizes multiple CPUs.
Java-based toolkit includes a high-level and low-level API, sample code, and complete documentation.
Integrated into a number of digital asset management applications.
Seeking snapshots in search results: November 9 2001 by
Gwendolyn Mariano Corbis, which sells digital images from its collection, announced implementation of the eVision visual search. Article includes a discussion of the general value of visual search.
Visual Search Engines: June 2001 by
Tony DeYoung Describes the value of finding similar pictures, such as stock photo libraries, e-commerce sites and auctions. Points out that pattern recognition has some value but tends to work better for simple images and small databases. Reports on the eVe image search technology, which separates each image into a collection of objects rather than a single thing and provides good user controls for defining the search. Image analysis is slow but search results are very fast.
eVe Demos - Three demos, each geared towards a different level of sophistication and experience with visual search.
ePhoto - Available as a free download for Mac OS X and Windows, the ePhoto application brings eVe digital image and video search technology to the individual desktop.