Shape Classification Using Tree -Unions
Published 1 August 2010
Bo Wang, Wei Shen, Wenyu Liu, Xinge You, Xiang Bai
Citations17
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
This paper proposes a novel approach to shape classification based on junction nodes that can represent the global structure in a simple way and illustrates the utility on the problem of 2D shape classification using the new shape tree representation.
Abstract
In this paper, we proposed a novel approach to shape classification. A new shape tree based on junction nodes can represent the global structure in a simple way. The statistic distribution of junctions can be learned by merging the shape trees. In the process of learning, context of a junction node is obtained to improve the rate of classification. We illustrate the utility of the proposed method on the problem of 2D shape classification using the new shape tree representation.
Keywords
Computer Science
IEEE Transactions on Pattern Analysis and Machine IntelligenceShape matching and object recognition using shape contexts
6,289 Citations2002Serge Belongie, Jitendra Malik +1 more
A novel approach to measuring similarity between shapes and exploiting it for object recognition by treating recognition in a nearest-neighbor classification framework as the problem of finding the stored prototype shape that is maximally similar to that in the image.
Journal of Theoretical BiologyBiological shape and visual science (part I)
1,160 Citations1973H.E. Blum
IEEE Transactions on Pattern Analysis and Machine IntelligenceShape Classification Using the Inner-Distance
1,071 Citations2007Haibin Ling, David W. Jacobs
It is suggested that the inner-distance can be used as a replacement for the Euclidean distance to build more accurate descriptors for complex shapes, especially for those with articulated parts.
International Journal of Computer VisionShock Graphs and Shape Matching
762 Citations1999Kaleem Siddiqi, Ali Shokoufandeh +2 more
A novel tree matching algorithm is introduced which finds the best set of corresponding nodes between two shock trees in polynomial time and is demonstrated under articulation, occlusion, and moderate changes in viewpoint.
IEEE Transactions on Pattern Analysis and Machine IntelligenceSkeleton Pruning by Contour Partitioning with Discrete Curve Evolution
426 Citations2007Xiang Bai, Longin Jan Latecki +1 more
IEEE Transactions on Pattern Analysis and Machine IntelligencePath Similarity Skeleton Graph Matching
340 Citations2008Xiang Bai, Longin Jan Latecki
A novel graph matching algorithm is proposed and applies it to shape recognition based on object silhouettes by comparing the geodesic paths between skeleton endpoints by motivated by the fact that visually similar skeleton graphs may have completely different topological structures.
Vision ResearchDetermining the similarity of deformable shapes
216 Citations1998Ronen Basri, Luiz Costa +2 more
Approximate tree matching and shape similarity
145 Citations1999Tyng-Luh Liu, Davi Geiger
A framework for 2D shape contour (silhouette) comparison that can account for stretchings, occlusions and region information is presented and three local tree matching operations, merge, cut, and merge-and-cut, are introduced to yield optimally approximate matches.
Signal ProcessingCurves vs. skeletons in object recognition
90 Citations2004Thomas Sebastian, Benjamin B. Kimia
The results indicate that the additional computational effort required in shock-graph matching is worthwhile in the presence of large amount variations, in particular those involving the presenceof articulation or rearrangement of parts.
IEEE Transactions on Pattern Analysis and Machine IntelligenceDisconnected Skeleton: Shape at Its Absolute Scale
81 Citations2008Cagri Aslan, Aykut Erdem +2 more
This work presents a new skeletal representation along with a matching framework to address the deformable shape recognition problem and replaces the local coordinate frame with a global Euclidean frame supported by additional mechanisms to handle articulations and local boundary deformations.
IEEE Transactions on Pattern Analysis and Machine IntelligenceLearning shape-classes using a mixture of tree-unions
74 Citations2006Andrea Torsello, Edwin R. Hancock
This paper adopts a minimum description length approach to the problem of fitting a mixture of tree unions to a set of sample trees, and makes maximum-likelihood estimates of the Bernoulli parameters.
Classification of Contour Shapes Using Class Segment Sets
73 Citations2005Ke Sun, Boaz J. Super
A part-based approach to address classes that have large nonlinear variability, especially when the variability is structural or due to articulation, which achieves 98% classification accuracy on a large database with many classes.
Object Class Recognition by Boosting a Part-Based Model
40 Citations2005Aharon Bar-Hillel, Tomer Hertz +1 more
A new technique for object class recognition is proposed, which learns a generative appearance model in a discriminative manner, based on the intermediate representation of an image as a set of patches, which are extracted using an interest point detector.
International Journal of Pattern Recognition and Artificial IntelligenceSKELETON-BASED SHAPE CLASSIFICATION USING PATH SIMILARITY
36 Citations2008Xiang Bai, Xing‐Wei Yang +2 more
Using a new skeleton pruning method, it is able to obtain stable pruned skeletons even in the presence of significant contour distortions, and a new method for matching of skeleton graphs is proposed.
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.Object recognition using segmentation for feature detection
17 Citations2004Michael Fussenegger, Andreas Opelt +2 more
A new method is presented to learn object categories from unlabeled and unsegmented images for generic object recognition using a new segmentation method - "similarity-measure segmentation" - to split the images into regions of interest.