Hough Networks for Head Pose Estimation and Facial Feature Localization
In Proceedings British Machine Vision Conference 2014
AbstractWe present Hough Networks (HNs), a novel method that combines the idea of Hough Forests (HFs) with Convolutional Neural Networks (CNNs). Similar to HFs we perform a simultaneous classification and regression on densely extracted image patches. But instead of a Random Forest we utilize a CNN which is able to learn higher-order feature representations and does not rely on any handcrafted features. Applying a CNN on a patch level has the advantage of reasoning about more image details and additionally allows to segment the image into foreground and background. Furthermore, the structure of a CNN supports efficient inference of patches extracted from a regular grid. We evaluate HNs on two computer vision tasks: head pose estimation and facial feature localization. Our method achieves at least state-of-the-art performance without sacrificing versatility which allows extension to many other applications.
FilesExtended Abstract (PDF, 1 page, 90K)
Paper (PDF, 12 pages, 237K)