Proceedings Article10.1109/ICDSP.1997.628441
A metamorphosis-based shape recognition method
Rahul Singh,J. Pavlidis,Nikolaos Papanikolopoulos +2 more
- 02 Jul 1997
- Vol. 2, pp 679-682
3
TL;DR: This work presents a framework for matching and recognition of planar shapes based on a method from computer graphics based animation, called "shape metamorphosis", which is shown to have metric properties and invariance to translation, rotation, scaling and mirror symmetry.
read more
Abstract: We present a framework for matching and recognition of planar shapes based on a method from computer graphics based animation, called "shape metamorphosis". In our approach, the "degree of morphing" between two shapes is employed as a dissimilarity measure. A physics-based energy minimization approach is used for optimally computing the "degree of morphing". This measure is shown to have metric properties and invariance to translation, rotation, scaling and mirror symmetry. Experimentations in the recognition of planar shapes, hand-drawn figures, and online cursive words indicate the robustness of the recognition paradigm.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Shape Matching of Planar and Spatial Curves for Part Inspection
TL;DR: In this article, the authors combine the concepts of differential geometry, geometric modeling, mechanics of deformable bodies and computer aided part inspection to propose a methodology of curve matching for computer aided inspection purpose.
Pose alignment of an eye-in-hand system using image morphing
Rahul Singh,Richard M. Voyles,David Littau,Nikolaos Papanikolopoulos +3 more
- 13 Oct 1998
TL;DR: A unified framework based on image morphing is introduced, to address the above problems and apply it to the task of translational and rotational alignment of an eye-in-hand system to planar objects or planar projections of 3D objects.
2
Energy Based Shape Matching of Surfaces
P. V. M. Rao,Prathmesh Bodas +1 more
- 01 Dec 2006
TL;DR: A new approach to shape matching of free-form surfaces using an analogy from structural mechanics is presented, which has a potential to be used for many engineering applications including computer vision.
1
References
HMM based online handwriting recognition
TL;DR: A more sophisticated handwriting recognition system that achieves a writer independent recognition rate of 94.5% on 3,823 unconstrained handwritten word samples from 18 writers covering a 32 word vocabulary is built.
321
2-D shape classification using hidden Markov model
TL;DR: The authors present a planar shape recognition approach based on the hidden Markov model and autoregressive parameters that segments closed shapes to make classifications at a finer level and does not have to be trained again when a new class of shapes is added.
195
Real-time 100 object recognition system
Shree K. Nayar,S.A. Nene,Hiroshi Murase +2 more
- 22 Apr 1996
TL;DR: A real-time vision system is described that can recognize 100 complex three-dimensional objects and its recognition rate was found to be 100% and object pose was estimated with a mean absolute error of 2.02 degrees and standard deviation of 1.67 degrees.
Multidimensional co-occurrence matrices for object recognition and matching
Vassili Kovalev,Maria Petrou +1 more
TL;DR: A novel method based on the automatic search of features that characterize a certain object class using a training set consisting of both positive and negative examples, falling under the general problems of texture recognition, texture defect detection, and shape recognition.
95
Segmenting Handwritten Signatures at Their Perceptually Important Points
F. P. Preparata,M. I. Shamos +1 more
- 01 Jan 1993
TL;DR: A new algorithm for segmenting continuous handwritten signatures sampled by a digested sample is described, well illustrated and tested on a number of signatures that quire different kinds of segmentation decisions.
56