Image analysis – Pattern recognition – Feature extraction
Reexamination Certificate
1998-08-05
2003-11-11
Grant, II, Jerome (Department: 2624)
Image analysis
Pattern recognition
Feature extraction
C382S202000, C358S001900
Reexamination Certificate
active
06647146
ABSTRACT:
The present invention relates to an image processing apparatus and method.
In many image processing applications, it is necessary to identify edges in an image, for example to enhance the edges to give them a better visual appearance, to segment an image, or to identify corner points which lie at the intersection of edges in the image.
Known edge detection techniques, for example as described in “Computer Graphics Principles and Practice” by Foley, van Dam, Feiner and Hughes, Second Edition, Addison-Wesley Publishing Company ISBN 0-201-12110-7, detect edges by identifying sharp changes in intensity in the image. Such techniques do not provide reliable results in many circumstances, however, particularly when used on images in which an edge has become broken, for example due to lighting, shadows or poor image quality.
One particular application in which edge detection may be used is the creation of three-dimensional computer models of a real-life object using at least two images of the object taken from different positions to determine the relative position of points on the object in two-dimensions and the relative “depth” of the points. To create such models, it is necessary to know the location in each image of points which represent the same actual point on the object. Such points can be determined by identifying corner points in each image and matching corner points from one image with the corner points in another image.
To enable matching points to be easily identified in the images, a number of known systems apply a grid pattern to the object before the images are taken so that the grid lines can be identified in the images and their points of intersection determined. Such a system is disclosed in WO-A-90/10194. Before grid lines can be automatically identified by the image processing system, however, WO-A-90/10194 discloses that it is necessary for a user to “patch” the lines to ensure that they are unbroken. This is particularly time consuming.
The present invention has been made with the above problems in mind, and aims to provide an apparatus and method for detecting edges in an image.
The present invention provides an image processing apparatus or method in which edges in an image are detected on the basis of edge orientation. Edge intensity may optionally be used, as well.
Of course, use of edge detection is not limited to the above applications and many other image processing applications exist where edge detection is used.
In many image processing applications, it is necessary to sub-divide or segment an image. Such applications include object recognition and image compression.
The present invention provides an image processing apparatus or method in which an image is segmented in dependence upon edge strengths in the image.
The present invention provides an image processing apparatus or method in which an image is divided into pieces by connecting points in dependence upon the strength of edges therebetween. The pieces may be non-overlapping.
In many image processing applications, it is necessary to process edges identified in an image to determine whether any of the edges cross, and to remove the cross-overs. Such applications include image segmentation, object recognition and image data compression.
The present invention provides an image processing apparatus or method in which signals defining edges and the strengths thereof are processed to remove crossovers between the edges by considering pairs of edges in decreasing strength order. If two edges are thought to cross, the edge with the lower strength is deleted.
REFERENCES:
patent: 3901595 (1975-08-01), Helava et al.
patent: 4175862 (1979-11-01), DiMatteo et al.
patent: 4654872 (1987-03-01), Hisano et al.
patent: 4695156 (1987-09-01), Taft
patent: 4803645 (1989-02-01), Ohtomo et al.
patent: 4825393 (1989-04-01), Nishiya
patent: 4935810 (1990-06-01), Nonami et al.
patent: 5052045 (1991-09-01), Peregrim
patent: 5144373 (1992-09-01), Moler
patent: 5166878 (1992-11-01), Poelstra
patent: 5173949 (1992-12-01), Peregrim
patent: 5202928 (1993-04-01), Tomita et al.
patent: 5307136 (1994-04-01), Saneyoshi
patent: 5381526 (1995-01-01), Ellson
patent: 5390291 (1995-02-01), Ohashi
patent: 5398292 (1995-03-01), Aoyama
patent: 5420971 (1995-05-01), Westerink
patent: 5454069 (1995-09-01), Knapp et al.
patent: 5519485 (1996-05-01), Ohtani et al.
patent: 5559334 (1996-09-01), Gupta et al.
patent: 5604529 (1997-02-01), Kuga et al.
patent: 5727093 (1998-03-01), Uchiyama
patent: 5734743 (1998-03-01), Matsugu et al.
patent: 0141706 (1990-04-01), None
patent: 0537021 (1993-04-01), None
patent: 0633550 (1995-01-01), None
patent: 0 733 996 (1996-09-01), None
patent: 0898245 (1999-02-01), None
patent: 901105 (1999-10-01), None
patent: 2328127 (1999-10-01), None
patent: 2244621 (1991-04-01), None
patent: 2253052 (1992-08-01), None
patent: 2257250 (1993-01-01), None
patent: 2270435 (1994-03-01), None
patent: 63-129478 (1988-06-01), None
patent: 8-029126 (1996-02-01), None
patent: 08147469 (1996-07-01), None
patent: 8-329252 (1996-12-01), None
patent: 8-329253 (1996-12-01), None
patent: 09245166 (1997-09-01), None
patent: 88/02518 (1988-04-01), None
patent: 88/04804 (1988-06-01), None
patent: 90/10194 (1990-09-01), None
patent: 91/15732 (1991-10-01), None
patent: 91/19265 (1991-12-01), None
patent: 92/06444 (1992-04-01), None
“A Multistage Stereo Method Giving Priority to Reliable Matching” Nakayama et al., Proceedings of the International conference on Robotics and Automation, Nice, May 12-14, 1992, vol. 2, No. Conf. 8, May 12, 1992, Institute of Electrical and Electronics Engineers, pp. 1753-1758.
“Feature Matching for Building Extraction from Multiple Views” Roux et al., Proceedings of the Computer Society Conference on Computer Vision and Pattern Recognition, Seattle, Jun. 21-23, 1994, Institute of Electrical and Electronics Engineers, p. 46-53.
“Hierarchical Stereo and Motion Correspondence using Feature Groupings” Venkateswar et al., International Journal of Computer Vision, vol. 15, No. 3, 1989, Jul. 15, 1995, pp. 245-269.
“Polyhedron Reconstruction using Three-View Analysis” Hung et al., Pattern Recognition, vol. 22, No. 3, 1989, pp. 231-246.
“A Pyramidal Data Structure for Triangle-Based Surface Description” L. De. Floriani, IEEE Comput. Graphics Appl. Mar. 1989.
“Adaptive Least Squares Correlation: A Powerful Image Matching Technique” A.W. Gruen, Photogrammetry Remote Sensing and Cartography 1985, pp. 175-187.
“Affine Analysis of Image Sequences” L.S. Shapiro, Cambridge University Press 1995, ISBN 0-521-55063-7, Sections 5, 7 and Appendix D.
“Closed-Form Solution of Absolute Orientation using Unit Quaternions” B.K.P. Horn, Journal of the Optical Society of America, 4(4): 629-649, Apr. 1987.
“Computer and Robot Vision vol. 1”, R.M. Haralick and L.G. Shapiro, Addison-Wesley Publishing Company, 1992, ISBN 0-201-10877-1 (V.1), pp. 337-346 & Section 8.
“Computer Graphics Principle and Practice”, Foley, van Dam, Feiner & Hughes, Second Edition, Addison-Wesley Publishing Company, Inc., ISBN 0-201-12110-7.
“Graphics Gems” A. Glassner, Academic Press Professional, 1990, ISBN 0-12-286166-3, Chapter 7.
“Motion and Structure from Two Perspective Views: Algorithms, Error Analysis and Error Estimation” J. Weng, T.S. Huang and N. Ahuja, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, No. 5, May 1989, pp. 451-476.
“Numerical Recipes in “C”” W.H. Press, S.A. Teukolsky, W.T. Vetterling and B.P. Flannery, 1992, ISBN 0-521-43108-5, PP. 412-420.
“Robust Detection of Degenerate Configurations whilist Estimating the Fundamental Matrix” P.H.S. Torr, A. Zisserman and S. Maybank, Oxford University Technical Report 2090/96.
“Scale-Space Theory in Computer Vision” Tony Lindeberg, Kluwer Academic Publisher, IBSN 0-7923-9418-6, pp. 158-160 & Chapter 4.
“Three-Dimensional Computer Vision” Faugeras, MIT Press, ISBN 0-262-06158-9, Chapter 10.
“Generalizing Epipolar-Plane Image Analysis for Non-Orthogonal and Varying View Directions” Baker et al., Image Understanding Workshop, Proceedings of a Workshop Held at Los Angeles, Californi
Davison Allan Joseph
Haslam Jane
Lyons Alexander Ralph
Rowe Simon Michael
Taylor Richard Ian
Canon Kabushiki Kaisha
Fitzpatrick ,Cella, Harper & Scinto
Grant II Jerome
LandOfFree
Image processing apparatus does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Image processing apparatus, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Image processing apparatus will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3145560