eVe (eVision Visual engine) is an advanced Visual Search
engine that includes analysis, storage, indexing, and search/retrieval
of images and video. Unlike a classical keyword-based search,
eVision software retrieves images by analyzing their perceptual
content. Images do not need to be viewed, interpreted, or
keyworded by humans.
breaks new ground in Visual Search by bringing automatic
segmentation to the commercial world. Segmentation is
the process by which an image is divided into regions, which
correspond approximately to objects or parts of objects in
an image. Once these object regions are identified, features
such as color, texture and shape are extracted. Similarity
comparisons are then made to other objects in other images.
To use an implementation of eVe, you can either give eVe
a sample query image, select an image from the Visual Vocabulary
selection, or enter a keyword and then "Zero In"
your search to find additional pictures based on visual similarity.
These results are ranked according to relevance, and can be
APIs, plug-ins, and applications that take advantage of the
eVision Visual Search Technology.
These 3 working demos of eVe will give you the opportunity to
try out eVision's Visual Search technology on real data. The
demos each address a different level of sophistication and features
that a developer can add to a visual search application.
How eVe is functionally and technically unique from other visual
Visual Search Technical Whitepaper (1.2MB pdf)
A technical overview of content-based image search technology,
the market size & need, and the unique solution offered
From "What is Visual Search?" to "What is Visual
The Art & Science
to obtaining good visual search results
Obtaining good visual search results is a combination of a clean database and some simple search heuristics.
The possibilities for software developers to customize eVe are