Processing and using digital images within eVe consists of the following four steps:
Preparing Images for
Analysis. Before starting and using eVe, you must first prepare the
images upon which you want to perform visual searches.
Analyzing and Comparing
Images. Before you can use eVe to search and retrieve an image from
a database or flat file, you must analyze that source image. During analysis,
eVe segments an image into distinct object regions, then generates scale-independent
descriptions of those regions, known as visual signatures. For information
about how to prepare images for analysis, see the Additional
Configuration section.
Storing Image Information.
eVe stores information about images in MediaObjects and MediaCollections.
A MediaObject contains a single image and all the information related
to that image. A MediaCollection is a container for multiple MediaObjects.
Indexing images. After visual signatures for images
are generated, they are organized in a proprietary indexing scheme for
extremely fast retrievals.
Searching for and Retrieving Images. After analyzing, storing, and indexing images, use eVes comprehensive visual search engine and types to enable easy to use visual searches within applications.
The following table lists the high- and low-level interface parts involved in each step:
Function |
High-Level API |
Low-Level API |
Analyze |
|
|
Store |
|
|
Index |
|
|
Search and Retrieve |
|
|
See the eVe SDK API Reference Guide for more information about the eVe SDKs low- and high-level APIs.