Image analysis – Pattern recognition – Classification
Reexamination Certificate
2011-03-08
2011-03-08
Werner, Brian P (Department: 2624)
Image analysis
Pattern recognition
Classification
C382S226000, C382S228000
Reexamination Certificate
active
07903883
ABSTRACT:
A local bi-gram model object recognition system and method for constructing a local bi-gram model and using the model to recognize objects in a query image. In a learning phase, the local bi-gram model is constructed that represents objects found in a set of training images. The local bi-gram model is a local spatial model that only models the relationship of neighboring features without any knowledge of their global context. Object recognition is performed by finding a set of matching primitives in the query image. A tree structure of matching primitives is generated and a search is performed to find a tree structure of matching primitives that obeys the local bi-gram model. The local bi-gram model can be found using unsupervised learning. The system and method also can be used to recognize objects unsupervised that are undergoing non-rigid transformations for both object instance recognition and category recognition.
REFERENCES:
patent: 6041133 (2000-03-01), Califano
patent: 6118887 (2000-09-01), Cosatto et al.
patent: 6393143 (2002-05-01), Pipitone
patent: 6747643 (2004-06-01), Happel
patent: 6807286 (2004-10-01), Krumm et al.
patent: 7043084 (2006-05-01), Beardsley
patent: 7099510 (2006-08-01), Jones et al.
patent: 2003/0128876 (2003-07-01), Yamaguchi
patent: 2004/0165775 (2004-08-01), Simon et al.
patent: 2005/0213818 (2005-09-01), Suzuki et al.
patent: 2006/0204079 (2006-09-01), Yamaguchi
patent: 2006/0228000 (2006-10-01), Miyajima et al.
patent: WO-2006001525 (2006-01-01), None
Brown, M., R. Szeliski, and S. Winder, Multi-image matching using multi-scale oriented patches, Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2003, pp. 510-517, vol. 1.
Brown, P. F., V. J. Della Pietra, P. V. Desouza, J. C. Lai and R. L. Mercer, Class-based n-gram models of natural language, Computational Linguistics, 1992, pp. 467-479, vol. 18, No. 4.
Carneiro, G. and D. Lowe, Sparse flexible models of local features, Proc of European Conf. on Computer Vision, 2006, pp. 29-43.
Comaniciu, D., P. Meer, Mean shift: A robust approach toward a feature space analysis, IEEE Trans. on Pattern Analysis and Mach. Intelligence, 2002, vol. 24, pp. 603-619.
Crandall, D., P. Felzenszwalb, D. Huttenlocher, Spatial priors for part-based recognition using statistical models, Proceedings of the 2005 IEEE Comp. Soc. Conf. on Comp. Vision and Pattern Recognition (CVPR'05), 2005, pp. 10-17.
Crandall, D.J. and D. P. Huttenlocher, Weakly supervised learning of part-based spatial models for visual object recognition, 2006, pp. 16-29.
Felzenszwalb, P.F., Representation and detection of deformable shapes, IEEE Transactions on Pattern Recognition and Machine Intelligence, 2005, pp. 208-220, vol. 27, No. 2.
Fergus, R., P. Perona, A. Zisserman, Object class recognition by unsupervised scale-invariant learning, Proc. of the IEEE Conf. on Comp. Vision and Pattern Recognition, 2003, pp. 264-271, vol. 2.
Harris, C., and M. Stephens, A combined corner and edge detector, ALVEY Vision Conf., 1988, pp. 147-151.
Kadir, T. and M. Brady, Scale, saliency and image description, Int'l J. of Comp. Vision, Nov. 2001, pp. 83-105, vol. 45, No. 2.
Lazebnik, S., C. Schmid, J. Ponce, Sparse texture representation using affine-invariant neighborhoods, Proc. of the Conf. on Computer Vision and Pattern Recognition, 2003, vol. 2, pp. 319-324, Madison, Wisconsin, USA.
Li, Y., Y. H. Tsin, Y. Genc and T. Kanade, Statistical shape models for object recognition and part localization, 2006, pp. 699, vol. 2.
Lowe, D., Distinctive image features from scale-invariant keypoints, Int'l. J. of Comp. Vision, 2004, vol. 60, No. 2, pp. 91-110.
Matas, J., O. Chum, M. Urban and T. Pajdla, Robust wide-baseline stereo from maximally stable extremal regions, Image and Vision Computing, Sep. 1, 2004, pp. 761-767, vol. 22, No. 10.
Mikolajczyk, K. and C. Schmid, Scale and affine invariant interest point detectors, Int'l J. of Comp. Vision, 2004, pp. 63-86, vol. 60, No. 1.
Moreels, P., P. Perona, Probabilistic coarse-to-fine object recognition, submitted, Int'l J. of Comp. Vision, 2007.
Nistér, D., and H. Stewénius, Scalable recognition with a vocabulary tree, IEEE Conf. on Comp. Vision and Pattern Recognition (CVPR), Jun. 2006, vol. 2, pp. 2161-2168.
Pipitone, F., and W. Adams, Tripod operators for recognizing objects in range images: Rapid rejection of library objects, Proc. of the IEEE Conf. on Robotics and Automation, May 1992, pp. 1596-1601, vol. 2.
Pulli, K. and L. G. Shapiro, Triplet-based object recognition using synthetic and real probability models, Proc. of ICPR96, 1996, vol. IV, pp. 75-79.
Rothganger, F., S. Lazebnik, C. Schmid, and J. Ponce, 3D object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints, Int'l J. of Comp. Vision, Mar. 2006, pp. 231-259, vol. 66, No. 3.
Sivic, J., B. C. Russell, A. A. Efros, A. Zisserman, W. T. Freeman, Discovering objects and their location in images, Tenth IEEE International Conference on Computer Vision, Oct. 17-21, 2005, pp. 370-377, vol. 1.
Sivic, J. and A. Zisserman, Video Google: A text retrieval approach to object matching in videos, Proc. of the Int'l Conf. on Computer Vision, Oct. 2003, pp. 1470-1477, vol. 2.
Weber, M., M. Welling, and P. Perona, Unsupervised learning of models for recognition, European Conf. on Comp. Vision, 2000, pp. 18-32, vol. 1.
Lan Xiangyang
Szeliski Richard S.
Zitnick, III Charles Lawrence
Fischer Craig S.
Lyon & Harr L.L.P.
Microsoft Corporation
Werner Brian P
LandOfFree
Local bi-gram model for object recognition does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Local bi-gram model for object recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Local bi-gram model for object recognition will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2717023