Object detection and recognition system

Details Object detection and recognition system Object detection and recognition system

2011-03-22

2011-03-22

Ahmed, Samir A (Department: 2624)

Image analysis

Pattern recognition

C382S224000, C382S173000

Reexamination Certificate

active

07912288

ABSTRACT:
During a training phase we learn parts of images which assist in the object detection and recognition task. A part is a densely represented area of an image of an object to which we assign a unique label. Parts contiguously cover an image of an object to give a part label map for that object. The parts do not necessarily correspond to semantic object parts. During the training phase a classifier is learnt which can be used to estimate belief distributions over parts for each image element of a test image. A conditional random field is used to force a global part labeling which is substantially layout-consistent and a part label map is inferred from this. By recognizing parts we enable object detection and recognition even for partially occluded objects, for multiple-objects of different classes in the same scene, for unstructured and structured objects and allowing for object deformation.

REFERENCES:
patent: 7027620 (2006-04-01), Martinez
patent: 2006/0098871 (2006-05-01), Szummer
He et al: “Multiscale conditional random fields for image labeling”, in Proc. IEEE, CVPR'04, 2004.
Boykov et al: “Fast approximate energy minimization via graph cuts”, IEEE Trans. vol. 23, No. 11, 2001.
Agarwal, S. et al., “Learning a sparse representation for object detection”, In European Conference on Computer Vision, 2002.
Borenstein, E. et a., “Combining top-down and bottom-up segmentation”, In Proceedings IEEE workshop on Perceptual Organization in Computer Vision, CVPR 2004, 2004.
Crandall, D. et al., “Spatial priors for part-based recognition using statistical models”, In CVPR, 2005.
Fergus, R. et al., “Object class recognition by unsupervised scale-invariant learning”, In Computer Vision and Pattern Recognition, 2003.
Kumar, S. et al., “Discriminative random fields: A discriminative framework for contextual interaction in classification”, In ICCV, 2003.
Kumar, M.P. et al., “OBJ CUT”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Diego, 2005.
Lafferty, J. et al., “Conditional random fields: Probabilistic models for segmenting and labeling sequence data”, In International Conference on Machine Learning, 2001.
Leibe, B. et al., “Combined object categorization and segmentation with an implicit shape model”, In ECCV 2004 Workshop om Statistical Learning in Computer Vision, May 2004.
Partially Occluded Object Recognition Using Statistical Models http://www.springerlink.com/(cqvid2eimfi5xi45pkmnrhfq)/app/home/contribution.asp?referrer=parent&backto=issue,4,5;journal,54,191;linkingpublicationresults,1:100272,1.
Quattoni, A. et al., “Conditional random fields for object recognition”, In NIPS, 2004.
Shotton, J. et al., “Contour-based learning for object detection”, In ICCV, 2005.
Williams, O. M. C. et al., “The Variational Ising Classifier (VIC) algorithm for coherently contaminated data”, In Advances in Neural Information Processing Systems 17, pp. 1497-1504. MIT Press, Cambridge, MA, 2005.
Winn, J. et al., “LOCUS: Learning Object Classes with Unsupervised Segmentation”, In ICCV, 2005.

Affiliated with

Also associated with

Rating

Object detection and recognition system does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Object detection and recognition system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Object detection and recognition system will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2760558