eVision Logo
Visual Search Technology Unleashing the power of visual ebusiness
News Technology & Products Business Solutions Developers About eVision

Also See:

eVe SDK

Online Demo How To

eVe Getting Started FAQ

eVe Technical FAQ

eVision Newsgroup

Discussion Boards

 home > developers > documentation
eVe
SDK Developer Documentation

Install Guide
    pdf (322k)
This guide describes the steps for installing the eVe SDK. It contains instructions on installing the SDK under Win32, Linux, Mac OS X, IRIX and Solaris, configuring your database server, and verifying your installation.
Note: the eVe API install guide is included as part of the full eVe SDK download.

Getting Started Guide
    pdf (730k)
This document introduces you to conceptual information about digital images and content-based retrieval. You should be familiar with all the concepts in this document before you start programming with eVe.
Note: the eVe API getting started guide is included as part of the full eVe SDK download.

Reference Guide
    pdf (1.1 MB)
This guide discusses the eVe high-level API and its methods, the eVe low-level API and its interfaces and the three forms of EveException, differentiated by the number and type of their arguments.
Note: the eVe API reference is included as part of the full eVe SDK download.

  Complete Documentation available as HTML (will open in new window)


How to create the eVe HTML Online Demo
    A brief overview of the Java servlet-based eVe Online Web demo to dynamically construct the HTML pages delivered to the client web browser.

How to extract keyframes from a digital video for video indexing & search
    A brief overview of the Java servlet-based eVe Online Web demo to dynamically construct the HTML pages delivered to the client web browser.

About the eVe API:
eVision’s visual object recognition and extraction technology, implemented in the eVe engine, breaks images down into their key visual elements to generate and index visual signatures. It distills images into their representative visual characteristics based on colors, shapes, textures, and object regions. The algorithms employed segment an image into distinct object regions, then generate scale-independent descriptions of those regions, known as visual signatures. These visual signatures are organized in a proprietary indexing scheme for extremely fast retrievals. eVe can be seamlessly applied to index still and video images and any other digital patterns, such as audio tracks and seismographic data.

eVe is a building block for various imaging applications, rather than being an end-user application in itself. It consists of a set of Java (and soon C++ & COM) classes which provide access to methods for managing and processing image data.

The eVe high-level API is a set of Java wrappers. These wrappers abstract the functionality of the eVe low-level API into one class. The C++ and COM wrappers will also soon be available. Depending on your application requirements and development preferences, you can use either version of the high-level API.

The eVe low-level API gives you access to all of eVe’s power and functionality. If you want to perform a simple programming task, you may find it quicker to use the high-level API. However, if you want to perform more complicated tasks, or need to override system defaults, you must use the low-level API.