Real time skin-tone detection with a single-chip digital camera

Mi-Suen Lee*, Richard Kleihorst**, Anteneh Abbo**, and Eric Cohen-Solal*

*Philips Research USA, Briarcliff Manor, NY, USA.
**Philips Research Laboratories, Eindhoven, the Netherlands


This article describes a 30 frames/second VGA-format CMOS image sensor with an embedded massively parallel processor. The processor is fully programmable and therefore the sensor IC itself is able to run a variety of algorithms within close data vicinity of the sensor. Because of the parallel architecture comprising processor array and parallel memory accesses, high computational performances of up to 5 GOPS are achieved. This high performance allowed us to implement skin tone detection on the camera itself as part of a larger system for face recognition, releasing the host computer of cumbersome pixel processing tasks and minimizing the data transfer between camera and computer.

Paper in PDF format

Face/Hand Highligher

Step 1 (Sensor): Capture image

Step 2 (Xetal): Preprocessing

Step 3 (Xetal): Skin-tone detection

Step 4 (Xetal): Group into Region-of-Interest(ROI)

Step 5 (Application): Select relevant ROI using domain knowledge and highlight them