114
click to vote
ICPR
2002
IEEE
16 years 7 months ago
2002
IEEE
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...
128
click to vote
ICPR
2002
IEEE
16 years 7 months ago
2002
IEEE
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...
151
click to vote
ICPR
2002
IEEE
16 years 7 months ago
2002
IEEE
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...
147
click to vote
ICPR
2002
IEEE
16 years 7 months ago
2002
IEEE
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...
ICPR
2002
IEEE
16 years 7 months ago
2002
IEEE
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...
161
click to vote
ICPR
2002
IEEE
16 years 7 months ago
2002
IEEE
This paper presents a new kernel method for appearance-based object recognition, highly robust to noise and occlusion. It consists of a fully connected Markov Random Field that in...
151
click to vote
ICPR
2002
IEEE
16 years 7 months ago
2002
IEEE
This paper describes a method for quickly and robustly localizing the iris and pupil boundaries of a human eye in close-up images. Such an algorithm can be critical for iris ident...
162
click to vote
ICPR
2002
IEEE
16 years 7 months ago
2002
IEEE
We present our approach for scene classification in dense disparity maps from a binocular stereo system. The classification result is used for tracking and navigation purposes. Th...
128
click to vote
ICPR
2002
IEEE
16 years 7 months ago
2002
IEEE
Psychophysical studies have shown that humans actively exploit temporal information such as contiguity of images in object recognition. We have recently developed a recognition sy...