Deformable Template Matching within a Bayesian Framework for Hand-Written Graphic Symbol Recognition

2000 ◽  
pp. 193-208 ◽  
Author(s):  
Ernest Valveny ◽  
Enric Martí
Keyword(s):  
Template Matching ◽  
Bayesian Framework ◽  
Symbol Recognition ◽  
Deformable Template ◽  
Graphic Symbol

Application of Repeated GA to Deformable Template Matching in Cattle Images

2004 ◽  
pp. 134-145 ◽  
Author(s):  
Horacio M. González Velasco ◽  
Carlos J. García Orellana ◽  
Miguel Macías Macías ◽  
Ramón Gallardo Caballero ◽  
M. Isabel Acevedo Sotoca
Keyword(s):  
Template Matching ◽  
Deformable Template

Recognition of Human Shapes from Video Images by Deformable Template Matching and Neural Network

1998 ◽  
Vol 31 (29) ◽  
pp. 48
Author(s):  
Shunta Tate ◽  
Souichi Oka ◽  
Yoshiyasu Takefuji
Keyword(s):  
Neural Network ◽  
Template Matching ◽  
Deformable Template ◽  
Video Images

A proposal of improved lip contour extraction method using deformable template matching and its application to dental treatment

2007 ◽  
Vol 38 (5) ◽  
pp. 80-89 ◽  
Author(s):  
Yujin Yokogawa ◽  
Nobuo Funabiki ◽  
Teruo Higashino ◽  
Masashi Oda ◽  
Yoshihide Mori
Keyword(s):  
Template Matching ◽  
Extraction Method ◽  
Dental Treatment ◽  
Contour Extraction ◽  
Deformable Template

Generalized Deformable Models, Statistical Physics, and Matching Problems

1990 ◽  
Vol 2 (1) ◽  
pp. 1-24 ◽  
Author(s):  
Alan L. Yuille
Keyword(s):  
Template Matching ◽  
Statistical Physics ◽  
Probability Distributions ◽  
Combinatorial Problems ◽  
Global Constraints ◽  
Matching Problems ◽  
Deformable Template ◽  
Content Addressable Memories ◽  
Neural Network Theory ◽  
The Traveling Salesman Problem

We describe how to formulate matching and combinatorial problems of vision and neural network theory by generalizing elastic and deformable templates models to include binary matching elements. Techniques from statistical physics, which can be interpreted as computing marginal probability distributions, are then used to analyze these models and are shown to (1) relate them to existing theories and (2) give insight into the relations between, and relative effectivenesses of, existing theories. In particular we exploit the power of statistical techniques to put global constraints on the set of allowable states of the binary matching elements. The binary elements can then be removed analytically before minimization. This is demonstrated to be preferable to existing methods of imposing such constraints by adding bias terms in the energy functions. We give applications to winner-take-all networks, correspondence for stereo and long-range motion, the traveling salesman problem, deformable template matching, learning, content addressable memories, and models of brain development. The biological plausibility of these networks is briefly discussed.

Online graphic symbol recognition using neural network and ARG matching

2001 ◽  
Author(s):  
Bing Yang ◽  
Changhua Li ◽  
Weixing Xie
Keyword(s):  
Neural Network ◽  
Symbol Recognition ◽  
Graphic Symbol
Sign in / Sign up

Export Citation Format

Share Document