A Real-time, Embedded Face-Annotation System
Description
Face detection and recognition have numerous multimedia applications of broad interest, one of which is automatic face annotation. There exist many robust algorithms tackling these problems but most of these algorithms are computationally demanding and have only been implemented in PC- or server-based environments. In this work we show a real-time face-annotation system on a cellular-phone-based embedded platform.

We built our face annotation system on the Orchid Standard Carrier Board from the Toradex Corporation. This board consists of an Intel processor chip called the XScale PXA 320, and is based on the ARMv5TE architecture with a maximum clock rate of 806 MHz. We used a touch screen as the I/O device, and a webcam to capture still images.  This work applied OpenCV and ARENA as face detection and recognition algorithm.
System hardware overview:
User interface:


Detection result with annotation dialog window:
 


Recognition result:
Video demo
<back to research>