We present a new framework for recognizing planar object classes, which is based on local feature detectors and a probabilistic model of the spatial arrangement of the features. The allowed object deformations are represented through shape statistics, which are learned from examples. Instances of an object in an image are detected by finding the appropriate features in the correct spatial configuration. The algorithm is robust with respect to partial occlusion, detector false alarms, and missed features. A 94% success rate was achieved for the problem of locating quasi-frontal views of faces in cluttered scenes. 1 Introduction Many early pattern recognition algorithms were based on template matching , which is optimal for detecting a known signal in white noise. However, since the underlying assumption that "the signal is known exactly" rarely holds true, considerable effort has been devoted to extending this method to handle variability in the target signal. For example, approach...
user correction - Legacy Corrections
In Proc. IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn