Detection of Facial Landmarks of North Eastern Indian People

In this paper we worked on the automatic detection of the facial landmarks which includes left eye corners, right eye corners, left eyebrows, right eyebrows, lip corners, nostrils. In this paper, a procedure of automatic facial landmarks detection is presented. It consists of two modules: In first, a morphological opening operation is used to estimate the background. Then create a more uniform background by subtract the background image form original image. In the second module, the facial landmarks had been detected using a corner detector called Fast corner detector. In this case Fast corner detector technique is applied for detecting the facial landmarks, because corner detectors have been widely used as feature point detectors because Comers correspond to image locations with a high information content, and they can be matched between images. The Fast corner detector works on the corner response function (CRF), which is computed as a minimum change of intensity over all possible direction. The Fast corner detector is significantly faster to compute than other algorithms. Experiments have been done over the NorthEastern Face images, which is created by Biometric Laboratory of Computer Science and Engineering Department of Tripura University. In our Experiment we used 105 front images with different expression like Neutral, Anger, Surprise, Sad, Laughter, Fear, and Disgust. We found out the average mean error rate was 0.9619 of all images of different expression of Outer eye corners, Inner eye corners, Mouth corners, Outer eyebrows, Inner eyebrows, Nostrils.