Face detection and recognition with SURF for human-robot interaction

This paper describes a feature-based approach for face detection and recognition for human-robot interaction (HRI), which is capable of processing images rapidly and achieving high detection and recognition rates. The vision system on the mobile robot has to deal with difficult problems such as illumination changes, different facial expressions, and dynamic complex background. We apply an efficient method for detecting human face and extracting facial features for face recognition to solve the above problems. We locate the face region by employing some morphological steps after skin region detected. The face contour is obtained using an ellipse fitting method. Then we use SURF (Speeded-Up Robust Features) local descriptors to extract the features of elliptical face region. Finally, we match the query image with the database images and check the geometrical consistency. Experimental results with Caltech's face database show that our approach is able to detect and recognize different faces with different illumination/expressions/backgrounds rapidly and accurately. The results prove the usefulness of this algorithm in real-time face detection and recognition for human-robot interaction.