Image analysis – Pattern recognition – Classification
Patent
1995-04-20
1998-01-20
Johns, Andrew
Image analysis
Pattern recognition
Classification
382118, 382206, G06K 900, G06K 962, G06K 952, G06K 974
Patent
active
057108331
ABSTRACT:
Methods and apparatus for detecting instances of a selected object or object feature in a digitally represented scene utilize analysis of probability densities to determine whether an input image (or portion thereof) represents such an instance. The invention filters images of objects that, although in some ways similar to the object under study, fail to qualify as typical instances of that object. The invention is useful in the detection and recognition of virtually any multifeatured entity such as human faces, features thereof (e.g., eyes), as well as non-rigid and articulated objects such as human hands.
REFERENCES:
patent: 4259661 (1981-03-01), Todd
patent: 4752957 (1988-06-01), Maeda
patent: 4838644 (1989-06-01), Ochoa et al.
patent: 4998286 (1991-03-01), Tsujiuchi et al.
patent: 5101446 (1992-03-01), Resnikoff et al.
patent: 5111516 (1992-05-01), Nakano et al.
patent: 5164992 (1992-11-01), Turk et al.
patent: 5245675 (1993-09-01), Ferre et al.
patent: 5432864 (1995-07-01), Lu et al.
Kirby et al., 12 IEEE Trans. on Pattern Analysis and Machine Intelligence 103 (1990).
Kumar et al., 21 Optical Engineering 043 (1982).
Moghaddam Baback
Pentland Alex
Davis Monica S.
Johns Andrew
Massachusetts Institute of Technology
LandOfFree
Detection, recognition and coding of complex objects using proba does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Detection, recognition and coding of complex objects using proba, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Detection, recognition and coding of complex objects using proba will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-731392