Image analysis – Pattern recognition – Template matching
Reexamination Certificate
2001-12-21
2003-05-13
Johns, Andrew W. (Department: 2621)
Image analysis
Pattern recognition
Template matching
C382S118000, C382S180000, C382S181000, C382S190000, C382S218000
Reexamination Certificate
active
06563950
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates to technology for recognizing and analyzing objects that are shown in camera or video images. In particular, the present invention relates to technology which compensates for variability of images for different objects of the same type, or for images of the same object (due to differences in position, scale, orientation, pose, illumination, deformation, noise etc.).
BACKGROUND OF THE INVENTION
Techniques exist for analyzing captured images in order to perform image matching or other functions, such as the extraction of a fixed, sparse image representation from each image in an image gallery and for each new image to be recognized. Conventional techniques, however, require a great deal of computational power and time. When comparing a new image with all images stored in a gallery of thousands of images, each comparison requires a new, computationally-expensive matching process. There is a need for an image analysis technique that is more easily implemented.
SUMMARY OF THE INVENTION
It is therefore an objective of the present invention to provide a technique for image analysis that is more easily implemented than are conventional techniques, and which requires less computational power and time.
The present invention provides a process for image analysis. The process includes selecting a number M of images, forming a model graph from each of the number of images, such that each model has a number N of nodes, assembling the model graphs into a gallery, and mapping the gallery of model graphs into an associated bunch graph by using average distance vectors &Dgr;
ij
for the model graphs as edge vectors in the associated bunch graph, such that
Δ
i
,
j
=
1
M
∑
m
Δ
ij
m
.
where &Dgr;
ij
is a distance vector between nodes i and j in model graph m. A number M of jets is associated with each node of the associated bunch graph, and at least one jet is labeled with an attribute characteristic of one of the number of images. An elastic graph matching procedure is performed, wherein the graph similarity function is replaced by a bunch-similarity function S(G, G
I
) such that
S
(
G
,
G
I
)
=
1
N
∑
n
max
m
S
(
J
n
m
,
J
n
l
)
.
The model bunch graph may be manually prepared by associating a standard grid of points over an image, correcting node positions to fall over designated sites characteristic of the image, and extracting jets at the nodes. Object recognition may be performed by selecting a target image, extracting an image graph from the target image, comparing the target image graph to the gallery of model graphs to obtain a graph similarity S(G
M
, G
I
) such that
S
(
G
M
,
G
I
)
=
1
N
∑
n
S
(
J
n
M
,
J
n
I
)
-
λ
E
∑
e
(
Δ
x
_
e
M
-
Δ
x
_
e
I
)
2
;
and
identifying a model graph having a greatest graph similarity with the image graph.
REFERENCES:
patent: 4725824 (1988-02-01), Yoshioka
patent: 4805224 (1989-02-01), Koezuka et al.
patent: 4827413 (1989-05-01), Baldwin et al.
patent: 5168529 (1992-12-01), Peregrim et al.
patent: 5187574 (1993-02-01), Kosemura et al.
patent: 5220441 (1993-06-01), Gerstenberger
patent: 5333165 (1994-07-01), Sun
patent: 5383013 (1995-01-01), Cox
patent: 5430809 (1995-07-01), Tomitaka
patent: 5432712 (1995-07-01), Chan
patent: 5511153 (1996-04-01), Azarbayejani et al.
patent: 5533177 (1996-07-01), Wirtz et al.
patent: 5588033 (1996-12-01), Yeung
patent: 5625717 (1997-04-01), Hashimoto et al.
patent: 5680487 (1997-10-01), Markandey
patent: 5699449 (1997-12-01), Javidi
patent: 5714997 (1998-02-01), Anderson
patent: 5715325 (1998-02-01), Band et al.
patent: 5719954 (1998-02-01), Onda
patent: 5736982 (1998-04-01), Suzuki et al.
patent: 5764803 (1998-06-01), Jacquin et al.
patent: 5774591 (1998-06-01), Black et al.
patent: 5809171 (1998-09-01), Neff et al.
patent: 5828769 (1998-10-01), Burns
patent: 4406020 (1995-06-01), None
Akimoto, T., et al., “Automatic Creation of Facial 3D Models”, IEEE Computer Graphics & Apps., pp. 16-22, Sep. 1993.
Ayache, N. et al., “Rectification of Images of Binocular and Trinocular Stereovision”, Proc. Of 9th Int'l., Conference on Pattern Recognition, 1, pp. 11-16, Italy, 1988.
Belhumeur, P., “A Bayesian Approach to Binocular Stereopsis”,Int'l. J. Of Computer Vision, 19(3), pp. 237-260, 1996.
Beymer, D. J., “Face Recognition Under Varying Pose”, MIT A.I. Lab, Memo No. 1461, pp. 1-13, 12/93.
Beymer, D.J., “Face Recognition Under Varying Pose”, MIT A.I. Lab. Research Report, 1994, pp. 756-761.
Buhmann, J. et al., “Distortion Invariant Object Recognition By Matching Hierarchically Labeled Graphs”, In Proceedings IJCNN Int'l Conf. Of Neural Networks, Washington, D.C. Jun. 1989, pp. 155-159.
DeCarlo, D., et al., “The integration of Optical Flow and Deformable Models with Applications to Human Face Shape and Motion Estimation”, pp. 1-15, In Proc. CVPR '96, pp. 231-238 (published)[TM Sep. 18, 1996].
Devernay, F. et al., “Computing Differential Properties of 3-D Shapes from Steroscopic Images without {3-D} Models”, INRIA, RR-2304, pp. 1-28, Sophia, Antipolis, 1994.
Dhond, U., “Structure from Stereo: a Review”, IEEE Transactions on Systems, Man, and Cybernetics, 19(6), pp. 1489-1510, 1989.
Fleet, D.J., et al., “Computation of Component Image Velocity from Local Phase Information”,Int., J. Of Computer Vision, 5:1, pp. 77-104 (1990).
Fleet, D.J., et al.Measurement of Image Velocity, Kluwer Academic Press, Boston, pp. I-203, 1992.
Hall, E.L., “Computer Image Processing And Recognition”, Academic Press 1979, 99. 468-484.
Hong, H., et al., “Online Facial Recognition based on Personalized Gallery”, Proceedings of Int'l Conference On Automatic Face And Gesture Recognition, pp. 1-6, Japan Apr. 1997.
Kolocsai, P., et al, Statistical Analysis of Gabor-Filter Representation,Proceedings of International Conference on Automatic Face and Gesture Recognition, 1997, 4 pp.
Kruger, N., “Visual Learning with a priori Constraints”,Shaker Verlag, Aachen, Germany, 1998, pp. 1-131.
Kruger, N., et al, “Principles of Cortical Processing Applied to and Motivated by Artificial Object Recognition”, Institut fur Neuroinfomatik,Internal Report 97-17, Oct. 1997, pp. 1-12.
Kruger, N., et al, “Autonomous Learning of Object Representations Utilizing Self-Controlled Movements”, 1998,Proceedings of NN98, 5 pp.
Kruger, N., et al, “Object Recognition with a Sparse and Autonomously Learned Representation Based on Banana Wavelets”,Internal Report 96-11, Institut fur Neuroinfomatik, Dec. 96, pp. 1-24.
Kruger, N., et al, “Object Recognition with Banana Wavelets”,European Symposium on Artificial Neural Networks(ESANN97), 1997, 6 pp.
Kruger, N., “An Algorithm for the Learning of Weights in Discrimination Functions Using a priori Constraints”,IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, No. 7, Jul. 1997, pp. 764-768.
Lades, M., et al, “Distortion Invarient Object Recognition in the Dynamic Link Architecture”,IEEE Transactions on Computers, vol. 42, No. 3, 1993, 11 pp.
Luong, Q. T., et al, “The Fundamental Matrix, Theory, Algorithm, and Stability Analysis”,INRIA, 1993, pp. 1-46.
Manjunath, B. S., et al, “A Feature Based Approach to Face Recognition”,In Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 373-378, Mar. 1992.
Mauer, T., et al, “Single-View Based Recognition of Faces Rotated in Depth”,In Proceedings of the International Workshop on Automatic Face and Gesture Recognition, pp. 248-253, Zurich, CH, Jun. 26, 1995.
Mauer, T., et al, “Learning Feature Transformations to Recognize Faces Rotated in Depth”,In Proceedings of the International Conference on Artificial Neural Networks, vol. 1, pp. 353-358, Paris, France, Oct. 9-13, 1995.
Mauer, T., et al, “Tracking and Learning Graphs and Pose on Image Sequences of Faces”,Proceedings of 2nd International Conference on Automatic Face and Gesture Recognition, Oct. 14-16, 1996, pp. 176-181.
Maybank, S. J. et al, “A Theory of Self-Calibration of
Malsburg Christoph von der
Wiskott Laurenz
Eyematic Interfaces, Inc.
Gray Cary Ware & Freidenrich
Johns Andrew W.
Mariam Daniel G.
Meador Terrance A.
LandOfFree
Labeled bunch graphs for image 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 Labeled bunch graphs for image analysis, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Labeled bunch graphs for image analysis will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3022019