IDKit Multimodal SDK

The face recognition capabilities of the IFace SDK are accessible by means of the IDKit Server SDK platform, which uses the IFace SDK as a plugin.

Powerful features and benefits

Key features

The use of the SDK is made simple through the notion of user. A user is a collection of faces of one physical person. This is very universal, as you can associate many face images with a particular user. Through verification functions you can directly compare two users without needing to explicitly combine similarity scores from different images – this is done automatically by the SDK.

In addition, database management functions are available that enable to store and retrieve user information in/from a database. In the database, you may optionally store both face templates and face images. Face are not required for face recognition but it may be an interesting option to store them in the database and display them when the user is verified/identified. Another very convenient option is the possibility to store for each user custom application specific data, such as username, address, e-mail, etc. For enhanced security, you may optionally switch on the database encryption. In this case, all face templates, images and custom data are automatically encrypted by AES (Advanced Encryption Standard) cipher when they are stored in the database.

The IDKit library compares face images and calculates their similarity scores. Verification is also called “1 to 1 matching”. Various verification strategies are supported:

  • comparison of two face images (matching of a probe face with a referenced face)
  • comparison of multiple face images of the same person against one or multiple images

Sometimes, you need to find an unknown user in a database, knowing only one (or more) of its face images. You may perform this through identification functions. Identification functions search for an unknown face image or set of images in the whole database. Identification search can be performed in different ways:

  • identification of one particular face image
  • identification of multiple face images impressions (views) of the same physical person

Identification was optimized for speed. Thanks to the automatic memory mapping of the database content, no additional database access time occurs when an identification search is performed.

In addition, the IDKit library contains a proprietary high speed fingerprint identification algorithm, suitable for the most demanding applications. This allows the verification and identification to be performed by using both modalities with resulting partial scores and one overall fused score.

Simple Integration

As a stand-alone software solution, integration couldn’t be easier. Simply,

  1. call our libraries from your application,
  2. easily extract face templates,
  3. compare them with faces stored in a database,
  4. return a result of the comparison.

With the IDKit Multimodal SDK, you get to focus on what’s important – your application – and leave the biometrics expertise to us.

Operating System

Windows (32-bit, 64-bit): 2000, XP, Vista, 7, 8, Server

Linux (32-bit, 64-bit): Red Hat, Debian

API

C/C++

Connectors

.NET, Java

Sample Applications

C++, .NET, Java

Database

PostgreSQL, Oracle, MS SQL[1]

[1] Other DB types upon request

Encryption

AES (256bit)

Any questions?

Lets´s talk