Data processing: artificial intelligence – Neural network – Learning task
Reexamination Certificate
2007-05-15
2007-05-15
Starks, Jr., Wilbert L. (Department: 2129)
Data processing: artificial intelligence
Neural network
Learning task
C356S456000, C356S326000, C382S165000
Reexamination Certificate
active
11075257
ABSTRACT:
A hyper-spectral analysis method for characterizing or distinguishing diverse elements within hyper-spectral images. A plurality of patches of pixels from within the hyper-spectral images are extracted as being patches around pixels of the elements to be characterized or distinguished. The statistics of spectra for each patch of pixels are computed. A first classifier is computed from frequency-wise standard deviation of the spectra in each patch and a set of second classifiers are computed from principal components of the spectral in each patch. A combined classifier is computed based on the output of the first classifier and at least one of the second classifiers. The elements are characterized or distinguished based on the output of at least one of the classifiers, preferably the combined classifier.
REFERENCES:
patent: 4193691 (1980-03-01), Fjarlie
patent: 4448529 (1984-05-01), Krause
patent: 4790654 (1988-12-01), Clarke
patent: 5061049 (1991-10-01), Hornbeck
patent: 5323002 (1994-06-01), Sampsell et al.
patent: 5483335 (1996-01-01), Tobias
patent: 5504575 (1996-04-01), Stafford
patent: 5506676 (1996-04-01), Hendler et al.
patent: 5567937 (1996-10-01), Pinkus
patent: 5737075 (1998-04-01), Koch et al.
patent: 5748308 (1998-05-01), Lindberg et al.
patent: 5828066 (1998-10-01), Messerschmidt
patent: 5966460 (1999-10-01), Porter, III et al.
patent: 6018587 (2000-01-01), Cabib
patent: 6046808 (2000-04-01), Fateley
patent: 6128077 (2000-10-01), Jovin et al.
patent: 6128078 (2000-10-01), Fateley
patent: 6373568 (2002-04-01), Miller et al.
patent: 6640130 (2003-10-01), Freeman et al.
patent: 6992775 (2006-01-01), Soliz et al.
patent: 2002/0146160 (2002-10-01), Paker et l.
patent: 0916981 (1999-05-01), None
patent: WO-98/35211 (1998-08-01), None
Holden et al., Deconvolution of measured spectra based on principal components analysis and derivative spectroscopy, Geoscience and Remote Sensing Symposium Proceedings, 1998, IGARSS '98. 1998 IEEE international, vol. 2, Jul. 6-10, 1998 pp. 760-762.
Coifman Ronald R.
Coppi Andreas
Davis Gustave L.
Deverse Richard A.
Fateley William G.
Fulbright & Jaworski LLP
Plain Sight Systems, Inc.
Starks, Jr. Wilbert L.
LandOfFree
System and method for hyper-spectral analysis does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for hyper-spectral analysis, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for hyper-spectral analysis will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3745687