Rotation Invariant Neural Network-Based Face Detection

In this paper, we present a neural network-based face detection system. Unlike similar systems which are limited to detecting upright, frontal faces, this system detects faces at any degree of rotation in the image plane. The system employs multiple networks; the first is a "router" network which processes each input window to determine its orientation and then uses this information to prepare the window for one or more "detector" networks. We present the training methods for both types of networks. We also perform sensitivity analysis on the networks, and present empirical results on a large test set. Finally, we present preliminary results for detecting faces which are rotated out of the image plane, such as profiles and semi-profiles. This work was partially supported by grants from Hewlett-Packard Corporation, Siemens Corporate Research, Inc., the Department of the Army, Army Research Office under grant number DAAH04-94-G-0006, and by the Office

• Type: Conference
• Year: 1998
• Where: CVPR
• Authors: Henry A. Rowley, Shumeet Baluja, Takeo Kanade
• Keywords: Army Research Office, Computer Vision, CVPR 1998, Frontal Faces, Image Plane, Multiple Networks, Neural Network-Based Face