San Francisco, Ca.
June 18, 1996 to June 20, 1996
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.
computer vision, pattern recognition, object recognition, shape statistics, flexible, deformable, planar objects, point configurations, constellations, face localization, handwriting
M.C. Burl, P. Perona, "Recognition of Planar Object Classes", CVPR, 1996, 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013 IEEE Conference on Computer Vision and Pattern Recognition 1996, pp. 223, doi:10.1109/CVPR.1996.517078