Development of a robust face detection system for a mobile service robot

Automatic detection of human faces in the environment is essential and needed to develop a mobile service robot so that it can detect and communicate with surrounding humans. Since the use of shape geometrical features alone is not good enough for reliable detection, color cues are used to augment the reliability of face detector. While color adds new information, it is problematic due to the dependence of image colors on the ambient illumination. Reduction of the illumination effect on image colors is therefore an important preprocessing step if color information is to be utilized for face detection. The methods presented in the previous literature to account for the illumination changes requires that the possible and expected illumination conditions to be specified apriori and the system should be trained in some way to account for the expected image changes. We propose a system of illumination preprocessing that does not require neither prior knowledge nor experimentation with the illuminants. We use a simple attachment with the camera to measure the illumination color and the image colors are compensated for illumination changes in real time using the reflection from the reference attachment "nose". The system is implemented and experiments showed the success of the system to detect human faces despite moderate changes of the illumination conditions.