Direct Analytical Methods for Solving Poisson Equations in Computer Vision Problems
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape quantization and recognition with randomized trees
Neural Computation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multigrid
Shape Matching and Object Recognition Using Shape Contexts
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shock-Based Indexing into Large Shape Databases
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Order Structure, Correspondence, and Shape Based Categories
Shape, Contour and Grouping in Computer Vision
Sketches with Curvature: The Curve Indicator Random Field and Markov Processes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Visual Organization for Figure/Ground Separation
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Geometric Level Set Methods in Imaging,Vision,and Graphics
Geometric Level Set Methods in Imaging,Vision,and Graphics
Random Walks for Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape Classification Using the Inner-Distance
IEEE Transactions on Pattern Analysis and Machine Intelligence
A survey of advances in vision-based human motion capture and analysis
Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Drums, curve descriptors and affine invariant region matching
Image and Vision Computing
Pose Insensitive 3D Retrieval by Poisson Shape Histogram
ICCS '07 Proceedings of the 7th international conference on Computational Science, Part II
3D shape recursive decomposition by Poisson equation
Pattern Recognition Letters
A Rotation-Invariant Approach to 2D Shape Representation Using the Hilbert Curve
ICIAR '09 Proceedings of the 6th International Conference on Image Analysis and Recognition
Appearance modeling using a geometric transform
IEEE Transactions on Image Processing
Decomposition for efficient eccentricity transform of convex shapes
CAIP'07 Proceedings of the 12th international conference on Computer analysis of images and patterns
Computing the eccentricity transform of a polygonal shape
CIARP'07 Proceedings of the Congress on pattern recognition 12th Iberoamerican conference on Progress in pattern recognition, image analysis and applications
Euclidean eccentricity transform by discrete arc paving
DGCI'08 Proceedings of the 14th IAPR international conference on Discrete geometry for computer imagery
An improved coordinate system for point correspondences of 2D articulated shapes
DGCI'09 Proceedings of the 15th IAPR international conference on Discrete geometry for computer imagery
Hitting the right paraphrases in good time
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Comparing evaluation protocols on the KTH dataset
HBU'10 Proceedings of the First international conference on Human behavior understanding
3D shape retrieval by Poisson histogram
Pattern Recognition Letters
Matching 2D and 3D articulated shapes using the eccentricity transform
Computer Vision and Image Understanding
Integrating local action elements for action analysis
Computer Vision and Image Understanding
The eccentricity transform (of a digital shape)
DGCI'06 Proceedings of the 13th international conference on Discrete Geometry for Computer Imagery
Hi-index | 0.00 |
Silhouettes contain rich information about the shape of objects that can be used for recognition and classification. We present a novel approach that allows us to reliably compute many useful properties of a silhouette. Our approach assigns for every internal point of the silhouette a value reflecting the mean time required for a random walk beginning at the point to hit the boundaries. This function can be computed by solving Poisson's equation, with the silhouette contours providing boundary conditions. We show how this function can be used to reliably extract various shape properties including part structure and rough skeleton, local orientation and aspect ratio of different parts, and convex and concave sections of the boundaries. In addition to this we discuss properties of the solution and show how to efficiently compute this solution using multigrid algorithms. We demonstrate the utility of the extracted properties by using them for shape classification.