Chin contour estimation using modified Canny edge detector

A novel method to estimate the chin contour which is the curve that separates the chin region from the neck region of a human face is proposed. The method assumes that the face and neck region has been separated from the background and the locations of eyes, mouth, and nose are known. The proposed algorithm first estimates several possible chin locations. A modified Canny edge detector is then used to extract edges that possess properties to qualify themselves as parts of the chin contour. Using these estimated chin edges and chin locations, we obtain a number of curves as candidates of the chin contour. A confidence score that measures the likeliness of a curve being the actual chin contour is used to select the most likely candidate. Experimental results show that the proposed algorithm can extract the chin contours of human faces of different facial expressions with good accuracy and the estimated chin contours with high confidence score is useful for face recognition.