Sciweavers

ICPR
2002
IEEE
16 years 8 months ago
Text Segmentation and Recognition in Complex Background Based on Markov Random Field
Datong Chen, Jean-Marc Odobez, Hervé Bourla...
144
Voted
ICPR
2002
IEEE
16 years 8 months ago
A Dynamic Programming Approach for Appearance-Based Recognition of Environments
Chu-Song Chen, Jiun-Hung Chen, Wen-Teng Hsieh
ICPR
2002
IEEE
16 years 8 months ago
Speeding up SVM Decision Based on Mirror Points
In this paper, we propose a new method to speed up SVM decision based on the idea of mirror points. Decisions based on multiple simple classifiers, which are formed as a result of...
Jiun-Hung Chen, Chu-Song Chen
ICPR
2002
IEEE
16 years 8 months ago
Learning and Extracting Edges from Images by a Modified Hopfield Neural Network
This paper introduced a modified unsupervised Hopfield network that can learn the underlying process in an edge detection task from grey level images. After the learning phase, th...
Sylvain Chartier, Richard Lepage
ICPR
2002
IEEE
16 years 8 months ago
Hierarchical Recognition of Intentional Human Gestures for Sports Video Annotation
We present a novel technique for the recognition of complex human gestures for video annotation using accelerometers and the hidden Markov model. Our extension to the standard hid...
Graeme S. Chambers, Svetha Venkatesh, Geoff A. W. ...
166
Voted
ICPR
2002
IEEE
16 years 8 months ago
Inexact Graph Matching Using Stochastic Optimization Techniques for Facial Feature Recognition
Roberto M. Cesar, Endika Bengoetxea, Isabelle Bloc...
ICPR
2002
IEEE
16 years 8 months ago
Graph of Neural Networks for Pattern Recognition
This paper presents a new architecture of neural networks designed for pattern recognition. The concept of induction graphs coupled with a divide-and-conquer strategy defines a Gr...
Hubert Cardot, Olivier Lezoray
ICPR
2002
IEEE
16 years 8 months ago
To Each According to its Need: Kernel Class Specific Classifiers
We present in this paper a new multi-class Bayes classifier that permits using separate feature vectors, chosen specifically for each class. This technique extends previous work o...
Barbara Caputo, Heinrich Niemann