26,386 Hits in 7.1 sec

Connected contours: A new contour completion model that respects the closure effect

Yansheng Ming, Hongdong Li, Xuming He
2012 2012 IEEE Conference on Computer Vision and Pattern Recognition  
This paper proposes a novel higher-order CRF model to address the contour closure effect, through local connectedness approximation.  ...  In contrast, much fewer methods have addressed the global contour closure effect, despite that many psychological evidences have shown the usefulness of closure in perceptual grouping.  ...  NICTA is a research center of excellence funded by the Australian Government, in part through ARC.  ... 
doi:10.1109/cvpr.2012.6247755 dblp:conf/cvpr/MingLH12 fatcat:cu2v6yietvhcpfaigdho6kjy4y

Convexity Grouping of Salient Contours [chapter]

Padraig Corcoran, Peter Mooney, James Tilton
2011 Lecture Notes in Computer Science  
This paper presents a new technique for contour grouping based on convexity and has the following two properties.  ...  The authors are unaware of any existing technique which exhibits either of these properties. Contour grouping is posed as the problem of finding minimum cost paths in a graph.  ...  the National Development Plan.  ... 
doi:10.1007/978-3-642-20844-7_24 fatcat:ri5cfrl25vdqnbl6hqdhau6vme

Contour Grouping Based on Contour-Skeleton Duality

Nagesh Adluru, Longin Jan Latecki
2009 International Journal of Computer Vision  
Regularizing contours and skeletons simultaneously allows us to combine both low level perceptual constraints as well as higher level model constraints in a very effective way.  ...  The models are represented using paths in symmetry sets.  ...  Acknowledgements We thank the anonymous reviewers for very insightful and constructive comments that helped to improve several aspects of our paper.  ... 
doi:10.1007/s11263-009-0208-2 fatcat:qf4wpqxqevahnhm42udtptfaqa

Hierarchical Contour Closure-Based Holistic Salient Object Detection

Qing Liu, Xiaopeng Hong, Beiji Zou, Jie Chen, Zailiang Chen, Guoying Zhao
2017 IEEE Transactions on Image Processing  
To better compute the saliency for complicated images, we propose a hierarchical contour closure based holistic salient object detection method, in which two saliency cues, i.e., closure completeness and  ...  The former pops out the holistic homogeneous regions bounded by completely closed outer contours, and the latter highlights the holistic homogeneous regions bounded by averagely highly reliable outer contours  ...  Though the running time of the closure completeness is more than that of the boundary connectivity [29] , the performance improvement that the closure completeness achieves is substantial. E.  ... 
doi:10.1109/tip.2017.2703081 pmid:28500000 fatcat:rxkjth3jqraqjcatmrzizzm6pe

Higher-Order Active Contour Energies for Gap Closure

Marie Rochery, Ian H. Jermyn, Josiane Zerubia
2007 Journal of Mathematical Imaging and Vision  
In this paper, we describe a higher-order active contour energy that in addition to favouring network-like regions, includes a prior term penalizing networks containing 'nearby opposing extremities', thereby  ...  provided that: • a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in  ...  The authors thank J.-A. Desideri for useful discussions and suggestions. We also thank the reviewers for their helpful comments, and one reviewer for the image in figure 21.  ... 
doi:10.1007/s10851-007-0021-x fatcat:7qymenbypffwvesvlmzep3fqwe

Structuring and layering contour drawings of organic shapes

Even Entem, Amal Dev Parakkat, Marie-Paule Cani, Loïc Barthe
2018 Proceedings of the Joint Symposium on Computational Aesthetics and Sketch-Based Interfaces and Modeling and Non-Photorealistic Animation and Rendering - Expressive '18  
(c) Manipulation of the depth ordering as desired (top), followed by the union of these elements composed with the original internal contours to produce a new drawing (bottom).  ...  To extract the structure, we introduce a new partaware metric for complex 2D drawings, the radial variation metric, which is used to identify salient sub-parts.  ...  This work was funded by the advanced grant EXPRESSIVE from the European Research Council (ERC-2011-ADG 20110209).  ... 
doi:10.1145/3229147.3229155 dblp:conf/npar/EntemPCB18 fatcat:zhwkfifymzcfnp2ff5ttuh5jmy

Cartesian contour

Ruoming Jin, Yang Xiang, Lin Liu
2009 Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '09  
Different from the existing works, this scheme provides a complete view of these itemsets by covering the entire collection of them.  ...  In addition, we consider several heuristic techniques to speedup the construction of Cartesian contour. The detailed experimental study demonstrates the effectiveness and efficiency of our approach.  ...  Table 5 , 6 and 7 show the results for real datasets connect, chess, and pumsb, respectively.  ... 
doi:10.1145/1557019.1557069 dblp:conf/kdd/JinXL09 fatcat:bpt55h3qazbmjgwung5stkqskq

Contour interpolation by vector-field combination

C. Fantoni, W. Gerbino
2003 Journal of Vision  
We model the visual interpolation of missing contours by extending contour fragments under a smoothness constraint.  ...  Model predictions fit psychophysical data on the effects of viewer-independent and viewer-dependent variables.  ...  However, the phenomenology of amodal completion indicates that image contours are not only grouped or chained.  ... 
doi:10.1167/3.4.4 pmid:12803537 fatcat:unfoyckrxzhl3n52uv4nnjlawu

Integration of contours: new insights

Robert Hess, David Field
1999 Trends in Cognitive Sciences  
What emerges is a new concept of a 'receptive field', in which the output of a neuron is a time-dependent, complex combination of feedforward, feedback and lateral connections that produce a rich description  ...  Psychophysical, neurophysiological and anatomical research of the last few years has converged on a new explanation of how the components of a contour become integrated.  ...  Acknowledgements We are indebted to the following for their collaborative contributions: Tony Hayes, Steven Dakin, Kathy Mullen, William McIlhagga and William Beaudot.  ... 
doi:10.1016/s1364-6613(99)01410-2 pmid:10562727 fatcat:22f3eezsv5czvdmgx5h4nq2a3y

Optimal Contour Closure by Superpixel Grouping [chapter]

Alex Levinshtein, Cristian Sminchisescu, Sven Dickinson
2010 Lecture Notes in Computer Science  
Detecting contour closure, i.e., finding a cycle of disconnected contour fragments that separates an object from its background, is an important problem in perceptual grouping.  ...  We introduce a new formulation of the problem, by transforming the problem of finding cycles of contour fragments to finding subsets of superpixels whose collective boundary has strong edge support in  ...  This work was supported in part by the European Commission under a Marie Curie Excellence Grant MCEXT-025481 (Cristian Sminchisescu) and NSERC (Alex Levinshtein, Sven Dickinson).  ... 
doi:10.1007/978-3-642-15552-9_35 fatcat:h4wpbhk7djahfjgqg2ihrwx4fe

Contour grouping with prior models

J.H. Elder, A. Krupnik, L.A. Johnston
2003 IEEE Transactions on Pattern Analysis and Machine Intelligence  
We introduce a framework for combining prior probabilistic knowledge of the appearance of the object with probabilistic models for contour grouping.  ...  A significant advantage of our formulation is that it rigorously combines probabilistic local cues with important global constraints such as simplicity (no self-intersections), closure, completeness, and  ...  One key to computing complete contours is the effective use of the constraint of closure.  ... 
doi:10.1109/tpami.2003.1201818 fatcat:6w472rym2ze2vf6hhq7s3d3iym

Cost-based closed-contour representations

Boris X. Vintimilla
2007 Journal of Electronic Imaging (JEI)  
The local scheme finally generates closed contours, linking open boundaries, by using a local cost function that takes into account both spatial and topological information.  ...  The global scheme computes an initial representation by connecting edge points minimizing a global measure based on spatial information (3D space).  ...  The first author ͑A.D.S.͒ was supported by The Ramón y Cajal Program. The second author ͑B.X.V.͒ was partially supported by the ESPOL under the VLIR project, Component 8.  ... 
doi:10.1117/1.2731799 fatcat:kvn7ex2hmjcdhmo5jwddb2tfgi

Shape from Contour: Computation and Representation

James H. Elder
2018 Annual Review of Vision Science  
While feedforward discriminative deep neural network models currently produce the best predictions of object selectivity in higher areas of the object pathway, a generative model may be required to account  ...  More complete shape representations may involve recurrent processes that integrate local and global cues.  ...  While effective for comparing similar shapes, by their nature these global transformations cannot completely describe a shape and cannot model parts.  ... 
doi:10.1146/annurev-vision-091517-034110 pmid:30222530 fatcat:mwhcyypwpvehxk5l5i7bc2rkbi

Contour Segments from Spline Interpolation [chapter]

Niklas Ludtke, Richard C. Wilson
2004 Lecture Notes in Computer Science  
In this paper we describe a method for grouping edge segments into perceptually salient contours using splines.  ...  Consistent structure is then identified using both perceptual criteria and similarity to contour structure in the image.  ...  In order to enforce smoothness of contours, it is necessary to impose a shape constraint on the connecting spline bundle that penalises a high degree of bending.  ... 
doi:10.1007/978-3-540-27868-9_13 fatcat:nksz4lxt3zbthk6tmsjp6u2x2e

Dynamic competition between contour integration and contour segmentation probed with moving stimuli

Jean Lorenceau, Anne Giersch, Peggy Seriès
2005 Vision Research  
Acknowledgments The pharmacological studies were financed by IN-SERM and by the University of Strasbourg. We thank Dr. Marie Welsch for the medical examination of the healthy volunteers.  ...  In this respect, our modelling effort may not offer a new architecture but serves to test the plausibility of our interpretation of the experimental results.  ...  This capability requires that disconnected segments of the same object are integrated into a single contour (contour completion and integration, e.g.  ... 
doi:10.1016/j.visres.2004.07.033 pmid:15571741 fatcat:qtqul54qlnhu7cayjfbgr3ykhq
« Previous Showing results 1 — 15 out of 26,386 results