IEEE Trans Image Process. 2016 Feb;25(2):580-8. doi: 10.1109/TIP.2015.2496183. Epub 2015 Oct 29.
In this paper, we present a novel approach to automatic 3D facial landmarking using 2D Gabor wavelets. Our algorithm considers the face to be a surface and uses map projections to derive 2D features from raw data. Extracted features include texture, relief map, and transformations thereof. We extend an established 2D landmarking method for simultaneous evaluation of these data. The method is validated by performing landmarking experiments on two data sets using 21 landmarks and compared with an active shape model implementation. On average, landmarking error for our method was 1.9 mm, whereas the active shape model resulted in an average landmarking error of 2.3 mm. A second study investigating facial shape heritability in related individuals concludes that automatic landmarking is on par with manual landmarking for some landmarks. Our algorithm can be trained in 30 min to automatically landmark 3D facial data sets of any size, and allows for fast and robust landmarking of 3D faces.
在本文中，我们提出了一种使用 2D 伽柏小波进行自动 3D 人脸地标定位的新方法。我们的算法将人脸视为一个表面，并使用地图投影从原始数据中提取 2D 特征。提取的特征包括纹理、地形图及其变换。我们扩展了一种已建立的 2D 地标定位方法，用于同时评估这些数据。该方法通过使用 21 个地标在两个数据集上进行地标定位实验进行验证，并与主动形状模型实现进行比较。我们的方法的地标定位误差平均为 1.9 毫米，而主动形状模型的地标定位误差平均为 2.3 毫米。第二项研究调查了相关个体的面部形状遗传性，得出结论认为，对于某些地标，自动地标定位与手动地标定位相当。我们的算法可以在 30 分钟内训练，以自动地标定位任何大小的 3D 面部数据集，并允许快速、稳健地标定位 3D 人脸。
