Object recognition using textons and shape filters

Details Object recognition using textons and shape filters Object recognition using textons and shape filters

2006-09-21

2010-11-23

Ahmed, Samir A. (Department: 2624)

Image analysis

Learning systems

C382S180000, C382S224000, C382S190000

Reexamination Certificate

active

07840059

ABSTRACT:
Given an image of structured and/or unstructured objects we automatically partition it into semantically meaningful areas each labeled with a specific object class. We use a novel type of feature which we refer to as a shape filter. Shape filters enable us to capture some or all of shape, texture and appearance context information. A shape filter comprises one or more regions of arbitrary shape, size and position within a bounding area of an image, paired with a specified texton. A texton comprises information describing the texture of a patch of surface of an object. In a training process we select a sub-set of possible shape filters and incorporate those into a conditional random field model of object classes. That model is then used for object detection and recognition.

REFERENCES:
patent: 2006/0098871 (2006-05-01), Szummer
patent: 2007/0223790 (2007-09-01), Xiao et al.
Kumar e et al: “Discriminative random field: a discriminative framework for contextual interaction in classification”, Ninth IEEE International Conference on Computer Vision (ICCV'03)—vol. 2, 2003.
He et al: “Multiscale conditional ramdom fields for image labeling”, in Proc. CVPR'04, IEEE, 2004.
Berg, A.C. et al., “Shape Matching and Object Recognition using Low Distortion Correspondences”, In: CVPR. (2005), 8 pages.
Borenstein, E. et al., “Combining Top-down and Bottom-up Segmentation”, In: Proceedings IEEE workshop on Perceptual Organization in Computer Vision, CVPR 2004, (2004), 8 pages.
Duygulu, P. et al., “Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary”,ECCV (2002), 15 pages.
Fergus, R. et al. “Object Class Recognition by Unsupervised Scale-Invariant Learning”, In: CVPR'03. vol. II. (2003) pp. 264-271.
He, X. et al. “Multiscale Conditional Random Fields for Image Labeling”. Proc. Of IEEE CVPR (2004), 8 pages.
Konishi, S. et al., “Statistical cues for Domain Specific Image Segmentation with Performance Analysis”, In: Proc. CVPR'2000 (2000), 13 pages.
Kumar, S. et al., “Discriminative Fields for Modeling Spatial Dependencies in Natural Images”, In: NIPS. (2004), 8 pages.
Kumar, S. et al. “Man-Made Structure Detection in Natural Images using a Causal Multiscale Random Field”, IEEE Int. Conf. on Computer Vision and Pattern Recognition (CVPR) (2003), 8 pages.
Kumar, P. et al., “OBJ CUT”, Proc. of IEEE CVPR, (2005), 61 pages.
Leibe, B. et al., “Interleaved Object Categorization and Segmentation”, In: BMVC'03, vol. II. (2003) 264-271, 10 pages.
Tu, Z. et al., “Image Parsing: Unifying Segmentation, Detection, and Recognition”, In: CVPR, (2003).
Winn, J. et al., “LOCUS: Learning Object Classed with Unsupervised Segmentation”, Proc. of IEEE ICCV, (2005), 8 pages.
Winn, J. et al., “Object Categorization by Learned Universal Visual Dictionary”, IEEE Int. Conf. of Computer Vision (2005), 8 pages.

Affiliated with

Also associated with

Rating

Object recognition using textons and shape filters 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 recognition using textons and shape filters, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Object recognition using textons and shape filters will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4231250