KeyLemonFaceSDK

Face Detection

KeyLemonFaceSDK can localize one or more faces in an image or a video (frontal face detection).

Requirements

• At least 30 pixels between eyes : subject at about a maximum of 1m from a standard webcam with a 320x240px stream (6 m for a fullHD stream with same FOV)
• At least 30 pixels between eyes

Computing Time and Memory Information

Face localization is very fast. The results presented below have been realized on images with a resolution of 320x240, on an Intel Core2 Duo E8500 @ 3.16GHz CPU and on an iPhone 4.

	Computer ("real time" algorithm)	Mobile ("mobile" algorithm)
Face Localization	17 [ms] -> 58 fps	17 [ms] -> 58 fps

Robustness

The library is robust to low resolution, slight light variation and face occlusion. It is also robust to beard variations, glasses changing, skin tone change ... Heavy side face lighting can compromise recognition. The background has no influence for face recognition.

The library can be embedded in multi-threaded applications too. This SDK have been used in several applications for years and all known bugs have been corrected.

Interface

The API is in C language with a full documentation. You can link with the library from almost any language (C, C++, C#, Java, VB, .NET...).

Sample Codes

Sample codes for detection and verification are provided along with the library with a clear documentation. Error codes are handled for debugging purpose.

Application Examples

• Person Tracking
• Presence Detection

KeyLemonFaceSDK

Build your own application Don't be left behing and get involved !

Request a license and get a trial period