Towards automatic landmarking on 2.5D face range images
Pui Suk Ting, Jacey-Lynn Minoi · 2013
In this paper, we propose an algorithm to automatically landmark points on 2.5-dimensional (2.5D) face images. We applied the Scale-invariant Feature Transform (SIFT) method to a new automatic landmarking method. Automatic landmarking has a number of added advantages over manual landmarking and it is more accurate and less time consuming especially if the dataset is large. We developed an interactive Graphical User Interface (GUI) tool to ease the visualization of the extract face features, which are scale and transformation invariant. The threshold values are then analyzed and generalized to best detect and extract important keypoints or/and regions of facial features. The results of the automatic extracted keypoint features are shown in this paper.