Facial landmarking locates the key facial feature points on facial data, which provides not only information on semantic facial structures, but also prior knowledge for other kinds of facial analysis. However, most of the existing works still focus on the 2D facial image which may suffer from lighting condition variations. In order to address this limitation, this paper presents a coarse-to-fine approach to accurately and automatically locate the facial landmarks by using deep feature fusion on 3D facial geometry data. Specifically, the 3D data is converted to 2D attribute maps firstly. Then, the global estimation network is trained to predict facial landmarks roughly by feeding the fused CNN (Convolutional Neural Network) features extracted from facial attribute maps. After that, input the local fused CNN features extracted from the local patch around each landmark estimated previously, and other local models are trained separately to refine the locations. Tested on the Bosphorus and BU-3DFE datasets, the experimental results demonstrated effectiveness and accuracy of the proposed method for locating facial landmarks. Compared with existed methods, our results have achieved state-of-the-art performance.
A surface detection algorithm with subvoxel accuracy is presented to extract edge and surface information from computed tomography (CT) images for virtual measurement and reverse engineering. The proposed algorithm employs the facet model and 3D IDDG operator to estimate the gradient vector and 3D directional derivatives. Subvoxel accuracy is achieved by locating the zeros of the 3D second directional derivative along the estimated gradient direction. Adaptive gradient threshold is used for the surface detector to improve the algorithm performance when applied to images with non-uniform contrast caused by CT artifacts, such as beam-hardening. Experiment results are presented to demonstrate the efficacy of the proposed method