Results 1  10
of
241
Contour and Texture Analysis for Image Segmentation
, 2001
"... 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 interveni ..."
Abstract

Cited by 404 (28 self)
 Add to MetaCart
(Show Context)
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.
Contour Detection and Hierarchical Image Segmentation
 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 2010
"... This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present stateoftheart algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our segmentati ..."
Abstract

Cited by 389 (24 self)
 Add to MetaCart
(Show Context)
This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present stateoftheart algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our segmentation algorithm consists of generic machinery for transforming the output of any contour detector into a hierarchical region tree. In this manner, we reduce the problem of image segmentation to that of contour detection. Extensive experimental evaluation demonstrates that both our contour detection and segmentation methods significantly outperform competing algorithms. The automatically generated hierarchical segmentations can be interactively refined by userspecified annotations. Computation at multiple image resolutions provides a means of coupling our system to recognition applications.
Learning a classification model for segmentation
 In Proc. 9th Int. Conf. Computer Vision
, 2003
"... We propose a twoclass classification model for grouping. Human segmented natural images are used as positive examples. Negative examples of grouping are constructed by randomly matching human segmentations and images. In a preprocessing stage an image is oversegmented into superpixels. We define a ..."
Abstract

Cited by 281 (2 self)
 Add to MetaCart
We propose a twoclass classification model for grouping. Human segmented natural images are used as positive examples. Negative examples of grouping are constructed by randomly matching human segmentations and images. In a preprocessing stage an image is oversegmented into superpixels. We define a variety of features derived from the classical Gestalt cues, including contour, texture, brightness and good continuation. Informationtheoretic analysis is applied to evaluate the power of these grouping cues. We train a linear classifier to combine these features. To demonstrate the power of the classification model, a simple algorithm is used to randomly search for good segmentations. Results are shown on a wide range of images. 1.
Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience
 Neural Computation
, 1995
"... We describe an algorithm and representation level theory of illusory contour shape and salience. Unlike previous theories, our model is derived from a single assumption namely, that the prior probability distribution of boundary completion shape can be modeled by a random walk in a lattice whose ..."
Abstract

Cited by 210 (14 self)
 Add to MetaCart
We describe an algorithm and representation level theory of illusory contour shape and salience. Unlike previous theories, our model is derived from a single assumption namely, that the prior probability distribution of boundary completion shape can be modeled by a random walk in a lattice whose points are positions and orientations in the image plane (i.e., the space which one can reasonably assume is represented by neurons of the mammalian visual cortex). Our model does not employ numerical relaxation or other explicit minimization, but instead relies on the fact that the probability that a particle following a random walk will pass through a given position and orientation on a path joining two boundary fragments can be computed directly as the product of two vectorfield convolutions. We show that for the random walk we define, the maximum likelihood paths are curves of least energy, that is, on average, random walks follow paths commonly assumed to model the shape of illusory co...
A Factorization Approach to Grouping
 in European Conference on Computer Vision
, 1998
"... The foreground group in a scene may be `discovered' and computed as a factorized approximation to the pairwise affinity of the elements in the scene. A pointwise approximation of the pairwise affinity information may in fact be interpreted as a `saliency' index, and the foreground of t ..."
Abstract

Cited by 173 (0 self)
 Add to MetaCart
(Show Context)
The foreground group in a scene may be `discovered' and computed as a factorized approximation to the pairwise affinity of the elements in the scene. A pointwise approximation of the pairwise affinity information may in fact be interpreted as a `saliency' index, and the foreground of the scene may be obtained by thresholding it. An algorithm called `affinity factorization' is thus obtained which may be used for grouping.
An Active Vision Architecture based on Iconic Representations
 Artificial Intelligence
, 1995
"... Active vision systems have the capability of continuously interacting with the environment. The rapidly changing environment of such systems means that it is attractive to replace static representations with visual routines that compute information on demand. Such routines place a premium on image d ..."
Abstract

Cited by 146 (13 self)
 Add to MetaCart
(Show Context)
Active vision systems have the capability of continuously interacting with the environment. The rapidly changing environment of such systems means that it is attractive to replace static representations with visual routines that compute information on demand. Such routines place a premium on image data structures that are easily computed and used. The purpose of this paper is to propose a general active vision architecture based on efficiently computable iconic representations. This architecture employs two primary visual routines, one for identifying the visual image near the fovea (object identification), and another for locating a stored prototype on the retina (object location). This design allows complex visual behaviors to be obtained by composing these two routines with different parameters. The iconic representations are comprised of highdimensional feature vectors obtained from the responses of an ensemble of Gaussian derivative spatial filters at a number of orientations and...
Deformable kernels for early vision
, 1991
"... Early vision algorithms often have a first stage of linearfiltering that 'extracts' from the image information at multiple scales of resolution and multiple orientations. A common difficulty in the design and implementation of such schemes is that one feels compelled to discretize coarsel ..."
Abstract

Cited by 145 (10 self)
 Add to MetaCart
Early vision algorithms often have a first stage of linearfiltering that 'extracts' from the image information at multiple scales of resolution and multiple orientations. A common difficulty in the design and implementation of such schemes is that one feels compelled to discretize coarsely the space of scales and orientations in order to reduce computation and storage costs. This discretization produces anisotropies due to a loss of traslation, rotation, scalinginvariance that makes early vision algorithms less precise and more difficult to design. This need not be so: one can compute and store efficiently the response of families of linear filters defined on a continuum of orientations and scales. A technique is presented that allows (1) to compute the best approximation of a given family using linear combinations of a small number of 'basis' functions; (2) to describe all finitedimensional families, i.e. the families of filters for which a finite dimensional representation is possible with no error. The technique is based on singular value decomposition and may be applied to generating filters in arbitrary dimensions. Experimental results are presented that demonstrate the applicability of the technique to generating multiorientation multiscale 2D edgedetection kernels. The implementation issues are also discussed.
From Contours to Regions: An Empirical Evaluation
"... We propose a generic grouping algorithm that constructs a hierarchy of regions from the output of any contour detector. Our method consists of two steps, an Oriented Watershed Transform (OWT) to form initial regions from contours, followed by construction of an Ultrametric Contour Map (UCM) defining ..."
Abstract

Cited by 136 (10 self)
 Add to MetaCart
We propose a generic grouping algorithm that constructs a hierarchy of regions from the output of any contour detector. Our method consists of two steps, an Oriented Watershed Transform (OWT) to form initial regions from contours, followed by construction of an Ultrametric Contour Map (UCM) definingahierarchicalsegmentation. We provideextensive experimentalevaluationtodemonstratethat, when coupled to a highperformance contour detector, the OWTUCM algorithm produces stateoftheart image segmentations. These hierarchical segmentations can optionally be further refined by userspecified annotations.
Ecological statistics of Gestalt laws for the perceptual organization of contours
, 2002
"... Although numerous studies have measured the strength of visual grouping cues for controlled psychophysical stimuli, little is known about the statistical utility of these various cues for natural images. In this study, we conducted eFperiments in which human participants trace perceived contours in ..."
Abstract

Cited by 100 (6 self)
 Add to MetaCart
(Show Context)
Although numerous studies have measured the strength of visual grouping cues for controlled psychophysical stimuli, little is known about the statistical utility of these various cues for natural images. In this study, we conducted eFperiments in which human participants trace perceived contours in natural images. These contours are automatically mapped to seGuences of discrete tangent elements detected in the image. By eFamining relational properties between pairs of successive tangents on these traced curves, and between randomly selected pairs of tangents, we are able to estimate the likelihood distributions reGuired to construct an optimal Bayesian model for contour grouping. We employed this novel methodology to investigate the inferential power of three classical Gestalt cues for contour groupingJ proFimity, good continuation, and luminance similarity. The study yielded a number of important resultsJ K1M these cues, when appropriately defined, are approFimately uncorrelated, suggesting a simple factorial model for statistical inferenceN K2M moderate imagetoimage variation of the statistics indicates the utility of general probabilistic models for perceptual organiQationN KRM these cues differ greatly in their inferential power, proFimity being by far the most powerfulN and KSM statistical modeling of the proFimity cue indicates a scaleinvariant power law in close agreement with prior psychophysics.