Method for recognizing objects in an image pixel plane

Details Method for recognizing objects in an image pixel plane Method for recognizing objects in an image pixel plane

2005-09-13

2005-09-13

Dastouri, Mehrdad (Department: 2623)

Image analysis

Pattern recognition

Classification

C382S280000, C382S156000

Reexamination Certificate

active

06944342

ABSTRACT:
Image data of optically acquired input images (1) are processed for emphasizing at least two object classes. Each pixel is subjected to a rough classification (10) based on first criteria that determine whether or not a pixel is relevant for an object recognition. A reduced image (11) is formed from the relevant pixels and irrelevant pixels are omitted. The reduced image (11) is filtered (20) for forming at least two correlated filtered images (21, 22, 23) based on second criteria. Classified images (31A,32A,33A) are formed from the filtered images by classifiers that work in accordance with predetermined rules. Weighting factors are allocated to each object class. The classified images are merged in accordance with an algorithm to make a combined global evaluation for each object class. The global evaluation decides, based on the merged images (41A,41B,41C), for each pixel whether the respective pixel belongs to an object class and if so to which object class.

REFERENCES:
patent: 4881270 (1989-11-01), Knecht et al.
patent: 5247584 (1993-09-01), Krogmann
patent: 5465308 (1995-11-01), Hutcheson et al.
patent: 5640468 (1997-06-01), Hsu
patent: 5835901 (1998-11-01), Duvoisin et al.
patent: 5838816 (1998-11-01), Holmberg
patent: 5911002 (1999-06-01), Mitsuyama et al.
patent: 5937078 (1999-08-01), Hyland et al.
patent: 5956427 (1999-09-01), Greenspan et al.
patent: 5963653 (1999-10-01), McNary et al.
patent: 6038337 (2000-03-01), Lawrence et al.
patent: 6042050 (2000-03-01), Sims et al.
patent: 6243492 (2001-06-01), Kamei
patent: 6263103 (2001-07-01), Freeman et al.
patent: 6393137 (2002-05-01), Chen et al.
patent: 6529614 (2003-03-01), Chao et al.
patent: 6556708 (2003-04-01), Christian et al.
patent: 6597800 (2003-07-01), Murray et al.
patent: 4438235 (1996-05-01), None
patent: 19639884 (2000-09-01), None
Practice of Digital Image Processing and Pattern Recognition by P. Haberaecker, published by Carl Hanser Verlag, 1995 (“Praxis der Digitalen Bildverarbeitung und Mustererkennung”); pp. 125 to 168.
“Automatic Target Detection and Recognition”, T. Dodd, University of Southhampton, Technical Report ISIS TR-4, pp. 1-19.
“Classifier and Shift-invariant Automatic Target Recognition Neural Networks”, David P. Casenant and Leonard m. Neiberg, Pergamon, 1995 Special Issue, pp. 1117-1128.
“Machine Learning Research”, Thomas G. Dietterich, AI Magazine, Winter 1997, pp. 97-133.
“Vehicle Detection in Infrared Linescan Imagery using Belief Networks”, P.G. Ducksbury, D.M. Booth, C.J. Radford, 5thInt. Conf. Image Proc. and Applications, Heriot-Watt University, Edinburgh, Jul. 3-5, 1995, 5 pages.
“Automatic Target Recognition Using a Feature-Decomposition and Data-Decomposition Modular Neural Network” by L. Wang et al. IEEE Transactions on Image Processing, IEEE, New York, USA, vol. 7, No. 8, Aug. 1998; pp. 1113 to 1121, XP000768985.
“A Tutorial on Multisensor Integration and Fusion” by R. Luo et al., Signal Processing and System Control, Factory Automation, Pacific Grove, Proceedings of the Annual Conference of the Industrial Electronics Society, (IECON), New York, USA, Nov. 27-30, 1990, pp. 707-722, IEEE vol. 1, Conf. 16, XO010038257.
“Detection Filters and Algorithm Fusion for ATR”, by David Casasent et al., IEEE Transactions on Image Processing, IEEE New York, USA, vol. 6, No. 1, Jan. 1997, pp. 114-125, XP 000642456.

Affiliated with

Also associated with

Rating

Method for recognizing objects in an image pixel plane does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method for recognizing objects in an image pixel plane, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for recognizing objects in an image pixel plane will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3400115