Classification of Contour Shapes Using Class Segment Sets
Published 27 July 2005
Ke Sun, Boaz J. Super
Citations73
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 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.
Abstract
Both example-based and model-based approaches for classifying contour shapes can encounter difficulties when dealing with classes that have large nonlinear variability, especially when the variability is structural or due to articulation. This paper proposes a part-based approach to address this problem. Bayesian classification is performed within a three-level framework, which consists of models for contour segments, for classes, and for the entire database of training examples. The class model enables different parts of different exemplars of a class to contribute to the recognition of an input shape. The method is robust to occlusion and is invariant to planar rotation, translation, and scaling. Furthermore, the method is completely automated. It achieves 98% classification accuracy on a large database with many classes.
Keywords
Computer Science
Computer Vision and Image UnderstandingActive Shape Models-Their Training and Application
7,187 Citations1995T.F. Cootes, Chris Taylor +2 more
This work describes a method for building models by learning patterns of variability from a training set of correctly annotated images that can be used for image search in an iterative refinement algorithm analogous to that employed by Active Contour Models (Snakes).
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.
Advanced textbooks in control and signal processingPattern Classification
5,015 Citations2001Leo H. Chiang, Evan L. Russell +1 more
Shape descriptors for non-rigid shapes with a single closed contour
832 Citations2002Longin Jan Latecki, Rolf Lakämper +1 more
This paper reports on the MPEG-7 Core Experiment CE-Shape, which gave a unique opportunity to compare various shape descriptors for non-rigid shapes with a single closed contour and found that a more theoretical comparison of these descriptors seems to be extremely hard.
IEEE Transactions on Medical ImagingA minimum description length approach to statistical shape modeling
567 Citations2002Rhodri Davies, Carole Twining +3 more
Results are given for several different training sets of two-dimensional boundaries, showing that the proposed method constructs better models than other approaches including manual landmarking-the current gold standard and can be extended straightforwardly to three dimensions.
Computer Vision and Image UnderstandingA Survey Of Free-Form Object Representation and Recognition Techniques
508 Citations2001Richard J. Campbell, Patrick J. Flynn
This survey reviews recent literature on both the 3D model building process and techniques used to match and identify free-form objects from imagery to offer the computer vision practitioner new ways to recognize and localize free- form objects.
IEEE Transactions on Pattern Analysis and Machine IntelligenceShape similarity measure based on correspondence of visual parts
459 Citations2000Longin Jan Latecki, Rolf Lakämper
This work applied a cognitively motivated similarity measure to shape matching of object contours in various image databases and compared it to well-known approaches in the literature, justifying that the shape matching procedure gives an intuitive shape correspondence and is stable with respect to noise distortions.
IEEE Transactions on Pattern Analysis and Machine IntelligenceOn aligning curves
375 Citations2003Thomas Sebastian, Philip N. Klein +1 more
The optimal correspondence is found by an efficient dynamic-programming method both for aligning pairs of curve segments and pairs of closed curves, and is effective in the presence of a variety of transformations of the curve.
IEEE Transactions on Image ProcessingDistance sets for shape filters and shape recognition
243 Citations2003Cosmin Grigorescu, Nicolai Petkov
This work addresses two problems that are often encountered in object recognition: object segmentation, for which a distance sets shape filter is formulated, and shape matching, which is illustrated on printed and handwritten character recognition and detection of traffic signs in complex scenes.
IEEE Transactions on Pattern Analysis and Machine IntelligenceFlexible syntactic matching of curves and its application to automatic hierarchical classification of silhouettes
236 Citations1999Yoram Gdalyahu, Daphna Weinshall
This paper presents extensive experiments where the flexible algorithm to match curves under substantial deformations and arbitrary large scaling and rigid transformations, and defines a dissimilarity measure which is used in order to organize the image database into shape categories.
Lecture notes in computer scienceShock-Based Indexing into Large Shape Databases
96 Citations2002Thomas Sebastian, Philip N. Klein +1 more
This paper developed a coarse-scale approximate similarly measure which is a good first-order approximation of the similarly metric and is two orders of magnitude more efficient to compute, and developed an exemplar-based indexing scheme which discards a large number of non-matching shapes solely based on distance to exemplars, coarse scale representatives of each category.
IEEE Transactions on Pattern Analysis and Machine IntelligenceAutomatic construction of 2D shape models
85 Citations2001Nicolae Duta, Anil K. Jain +1 more
This work proposes a flexible point matching technique that takes into account both pose/scale differences and nonlinear shape differences and can serve as a fully automated substitute to the tedious and time-consuming manual 2D shape registration and analysis.
Computer Vision and Image Understanding3D Free-Form Object Recognition Using Indexing by Contour Features
25 Citations1998Jinlong Chen, George Stockman
The proposed recognition-by-alignment paradigm is a viable approach to many 3D object recognition problems and Bench tests and simulations show that many kinds of objects can be handled accurately and efficiently even in cluttered scenes.
IEEE Transactions on Pattern Analysis and Machine IntelligenceStrings: Variational deformable models of multivariate continuous boundary features
13 Citations2003S. Ghebreab, A.W.M. Smeulders
Strings have been compared with active shape models on 145 vertebra images, showing that strings produce better results when initialized close to the target boundary, and comparable results otherwise.