A Probabilistic Multi-scale Model for Contour Completion Based on Image Statistics
Lecture notes in computer sciencePublished 1 January 2002
Xiaofeng Ren, Jitendra Malik
Citations51
SJR quartileQ2
SJR score0.35
SNIP0.55
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A probabilistic multi-scale model for contour completion based on image statistics based on both the prior model of contour shape and the local likelihood model of image measurements is derived.
Abstract
We derive a probabilistic multi-scale model for contour completion based on image statistics. The boundaries of human segmented images are used as "ground truth". A probabilistic formulation of contours demands a prior model and a measurement model. From the image statistics of boundary contours, we derive both the prior model of contour shape and the local likelihood model of image measurements. We observe multi-scale phenomena in the data, and accordingly propose a higher-order Markov model over scales for the contour continuity prior. Various image cues derived from orientation energy are evaluated and incorporated into the measurement model. Based on these models, we have designed a multi-scale algorithm for contour completion, which exploits both contour continuity and texture. Experimental results are shown on a wide range of images.
Keywords
Computer Science
IEEE Transactions on Pattern Analysis and Machine IntelligenceStochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
17,980 Citations1984Stuart Geman, Donald Geman
The analogy between images and statistical mechanics systems is made and the analogous operation under the posterior distribution yields the maximum a posteriori (MAP) estimate of the image given the degraded observations, creating a highly parallel ``relaxation'' algorithm for MAP estimation.
IEEE Transactions on Pattern Analysis and Machine IntelligenceNormalized cuts and image segmentation
15,696 Citations2000Jianbo Shi, Jitendra Malik
A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
8,007 Citations2002David Martín, Charless C. Fowlkes +2 more
A database containing 'ground truth' segmentations produced by humans for images of a wide variety of natural scenes is presented and an error measure is defined which quantifies the consistency between segmentations of differing granularities.
International Journal of Computer VisionContour and Texture Analysis for Image Segmentation
1,091 Citations2001Jitendra Malik, Serge Belongie +2 more
This paper provides an algorithm for partitioning grayscale images into disjoint regions of coherent brightness and texture, and introduces a gating operator based on the texturedness of the neighborhood at a pixel to facilitate cue combination.
Normalized cuts and image segmentation
863 Citations2002Jianbo Shi, Jitendra Malik
This work treats image segmentation as a graph partitioning problem and proposes a novel global criterion, the normalized cut, for segmenting the graph, which measures both the total dissimilarity between the different groups as well as the total similarity within the groups.
Vision ResearchEdge co-occurrence in natural images predicts contour grouping performance
692 Citations2001Wilson S. Geisler, J. S. Perry +2 more
It is found that contour detection performance is quantitatively predicted by a local grouping rule derived directly from the co-occurrence statistics, in combination with a very simple integration rule that links the locally grouped contour elements into longer contours.
Pattern Recognition LettersFeature detection from local energy
653 Citations1987Maria Concetta Morrone, Robyn Owens
A more general definition of features such as edges, shadows and bars is developed, based on an analysis of the phase of the harmonic components, showing that these features always occur at points of maximum phase congruency.
Statistics of natural images and models
510 Citations2003Jinggang Huang, D. Mumford
Results ranging from the simplest single pixel intensity to joint distribution of 3 Haar wavelet responses are reported, which shed light on old issues such as the near scale-invariance of image statistics and some are entirely new.
IEEE Transactions on Pattern Analysis and Machine IntelligenceTrace inference, curvature consistency, and curve detection
481 Citations1989P. Parent, Steven W. Zucker
It is shown that recovery of the trace of a curve requires estimating local models for the curve at the same time, and that tangent and curvature information are sufficient, which make it possible to specify powerful constraints between estimated tangents to a curve.
Elastica and Computer Vision
448 Citations1994David Mumford
I want to discuss the problem from differential geometry of describing those plane curves C which minimize the integral α k^2 + β ds over variations of C which preserve the total length.
Neural ComputationStochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience
334 Citations1997Lance R. Williams, David W. Jacobs
International Journal of Computer VisionInferring global pereeptual contours from local features
305 Citations1996G. Guy, G�rard Medioni
This work addresses the problem of contour inference from partial data, as obtained from state-of-the-art edge detectors, and argues that in order to obtain more pereeptually salient contours, it is necessary to impose generic constraints such as continuity and co-curvilinearity.
Detecting and localizing edges composed of steps, peaks and roofs
213 Citations2002Pietro Perona, Jitendra Malik
A two-dimensional version of the approach is developed which has the property of being able to represent multiple edges at the same location and determine the orientation of each to any desired precision, which permits junctions to be localized without rounding.
Lecture notes in computer scienceComputing contour closure
181 Citations1996James H. Elder, Steven W. Zucker
It is shown that simple tangent cycles can be efficiently computed in natural images containing many local ambiguities, and that these cycles generally correspond to bounding contours in the image.
Lecture notes in computer scienceContour continuity in region based image segmentation
171 Citations1998Thomas Leung, Jitendra Malik
A way of incorporating curvilinear grouping into region-based image segmentation through normalized cut approach and results on a large variety of images are shown.
A computational model of neural contour processing: Figure-ground segregation and illusory contours
163 Citations2002F. Heitger, R. von der Heydt
It is shown that the model reproduces illusory contours in accurate agreement with perception and generates representations of occluding contours on images of natural scenes that are more complete and less cluttered by spurious connections of foreground and background than those obtained by conventional edge detection operators.
IEEE Transactions on Pattern Analysis and Machine IntelligenceEmbedding Gestalt laws in Markov random fields
123 Citations1999Song‐Chun Zhu
This paper provides a quantitative measure for the so-called nonaccidental statistics and, thus, justifies some empirical observations of Gestalt psychology by information theory.
Fundamental bounds on edge detection: an information theoretic evaluation of different edge cues
87 Citations2003S. Konishi, Alan Yuille +2 more
This work uses information theoretic measures to determine the effectiveness of a variety of different edge detectors working at multiple scales on black and white and color images and gives quantitative measures for the advantages of multi-level processing, for the use of chromaticity in addition to greyscale, and for the relative effectiveness of different detectors.
Stochastic completion fields: a neural model of illusory contour shape and salience
86 Citations2002Lance R. Williams, David W. Jacobs
An algorithm and representation-level theory of illusory contour shape and salience that 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 vector-field convolutions.
IEEE Transactions on Pattern Analysis and Machine IntelligenceCompletion energies and scale
68 Citations2000E. Sharon, Achi Brandt +1 more
Lecture notes in computer scienceDetection of general edges and keypoints
59 Citations1992L. Rosenthaler, F. Heitger +2 more
An ” edge quality” measure is derived which allows to test the validity of a general edge model and a detection scheme for keypoints is proposed based on an analysis of oriented energy channels using differential geometry.
Lecture notes in computer scienceFinding boundaries in natural images: A new method using point descriptors and area completion
32 Citations1998Serge Belongie, Jitendra Malik
An approach to image segmentation for natural scenes containing image texture is developed which consists of a novel means of describing points in natural images and an associated distance function for comparing these descriptors.
Computer Vision and Image UnderstandingComputing Stochastic Completion Fields in Linear-Time Using a Resolution Pyramid
7 Citations1999Lance R. Williams, J. Zweck +2 more
A linear-time algorithm for computing the likelihood that a completion joining two contour fragments passes through any given position and orientation in the image plane is described, which means that a solution which previously took one hour to compute can now be computed in about two minutes.
Lecture notes in computer scienceComputing stochastic completion fields in linear-time using a resolution pyramid
7 Citations1997Lance R. Williams, Tairan Wang +1 more
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Boundary detection using quadratic filters: performance criteria and experimental assessment</title>
7 Citations1992Pietro Perona, Jitendra Malik
A class of nonlinear filters, known as quadratic filters are appropriate for this task, while linear filters are not, and a series of performance criteria are derived for characterizing the SNR, localization, and multiple responses of these quadRatic filters in a manner analogous to Canny's criteria for linear filters.