This paper provides an algorithm for partitioning grayscale images into disjoint regions of coherent brightness and texture. Natural images contain both textured and untextured regions, so the cues of contour and texture differences are exploited simultaneously. Contours are treated in the intervening contour framework, while texture is analyzed using textons. Each of these cues has a domain of applicability, so to facilitate cue combination we introduce a gating operator based on the texturedness of the neighborhood at a pixel. Having obtained a local measure of how likely two nearby pixels are to belong to the same region, we use the spectral graph theoretic framework of normalized cuts to find partitions of the image into regions of coherent texture and brightness. Experimental results on a wide range of images are shown.
|
3011
|
Pattern Classification and Scene Analysis
– Duda, Hart
- 1973
|
|
2439
|
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
– Geman, Geman
- 1984
|
|
1827
|
A Computational Approach to Edge Detection
– Canny
- 1986
|
|
1136
|
Normalized Cuts and Image Segmentation
– Shi, Malik
|
|
1125
|
Vector Quantization and Signal Compression
– Gersho, Gray
- 1992
|
|
463
|
Optimal approximations by piecewise smooth functions and variational problems
– Mumford, Shah
- 1989
|
|
422
|
Spectral Graph Theory
– Chung
- 1997
|
|
260
|
Pyramid-based texture analysis/synthesis
– HEEGER, BERGEN
- 1995
|
|
224
|
P.: Preattentive texture discrimination with early vision mechanisms
– Malik, Perona
- 1990
|
|
214
|
Segmentation using eigenvectors: a unifying view
– Weiss
- 1999
|
|
173
|
A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
– Martin, Fowlkes, et al.
- 2001
|
|
172
|
Representation of local geometry in the visual system
– Koenderink, Doorn
- 1987
|
|
146
|
Textons, the elements of texture perception, and their interactions
– Julesz
- 1981
|
|
143
|
Pattern Classi and Scene Analysis
– Duda, Hart
- 1973
|
|
135
|
Trace Inference, Curvature Consistency, and Curve Detection
– Parent, Zucker
- 1989
|
|
117
|
stochastic completion fields: a neural model of illusory contour shape and salience
– Williams, Jacobs
- 1995
|
|
115
|
Spatial vision
– Valois
- 1988
|
|
113
|
Structural Saliency: the Detection of Globally Salient Structures using a Locally Connected Network
– Sha’ashua, Ullman
- 1988
|
|
112
|
Color- and texture-based images segmentation using em and its application to image querying and classification
– Carson, Belongie, et al.
- 1998
|
|
99
|
A computational framework for determining stereo correspondence from a set of linear spatial lters
– Jones, Malik
|
|
77
|
Feature detection in human vision: a phase-dependent energy model
– Morrone, Burr
- 1988
|
|
74
|
Gabor filters as texture discriminator
– Fogel, Sagi
- 1989
|
|
71
|
Feature detection from local energy
– Morrone, Owens
- 1987
|
|
63
|
Texture analysis using two-dimensional quadrature filters
– Knutsson, Granlund
- 1983
|
|
61
|
Recognizing surfaces using three dimensional textons
– Leung, Malik
- 1999
|
|
61
|
Detecting and localizing edges composed of steps, peaks and roofs
– Perona, Malik
- 1990
|
|
60
|
Inferring surfaces from images
– Binford
- 1981
|
|
60
|
Colorand texture-based image segmentation using EM and its application to content-based image retrieval
– Belongie, Carson, et al.
- 1998
|
|
57
|
Computing contour closures
– Elder, Zucker
- 1996
|
|
55
|
Non-parametric similarity measures for unsupervised texture segmentation and image retrieval
– Puzicha, Hofmann, et al.
- 1997
|
|
49
|
Textons, contours and regions: Cue integration in image segmentation
– MALIK, BELONGIE, et al.
- 1999
|
|
42
|
Robust and efficient detection of salient convex groups
– Jacobs
- 1996
|
|
41
|
On the optimal detection of curves in noisy pictures
– Montanari
- 1971
|
|
17
|
Operational significance of receptive field assemblies
– Koenderink
- 1988
|
|
10
|
Contour continuity in region-based image segmentation
– Leung, Malik
- 1998
|
|
8
|
Vector quantization for texture classification
– McLean
- 1993
|
|
8
|
Laws of organization in perceptual forms (partial translation
– Wertheimer
- 1938
|
|
7
|
Finding boundaries in natural images: A new method using point descriptors and area completion
– Belongie, Malik
- 1998
|
|
7
|
Unsupervised texture classification using vector quantization and deterministic relaxation neural network
– Raghu, Poongodi, et al.
- 1997
|
|
6
|
Robust and ecient detection of salient convex groups
– Jacobs
- 1996
|
|
6
|
Stochastic completion a neural model of illusory contour shape and salience
– Williams, Jacobs
- 1997
|
|
2
|
Gabor as texture discriminator
– Fogel, Sagi
- 1989
|
|
2
|
Operational signi of receptive assemblies
– Koenderink, Doorn
- 1988
|
|
2
|
Finding boundaries in images
– Malik, Perona
- 1992
|
|
1
|
Texture Analysis for Image Segmentation 29
– Contour
- 1995
|
|
1
|
Texture Analysis 27
– Contour
- 1987
|
