A Trainable Low-level Feature Detector

P M Hall; M J Owen; J P Collomosse

A Trainable Low-level Feature Detector

P M Hall, M J Owen, J P Collomosse

Department of Computer Science

Research output: Contribution to conference › Paper

5 Citations (SciVal)

Abstract

We introduce a trainable system that simultaneously filters and classifies low-level features into types specified by the user. The system operates over full colour images, and outputs a vector at each pixel indicating the probability that the pixel belongs to each feature type. We explain how common features such as edge, corner, and ridge can all be detected within a single framework, and how we combine these detectors using simple probability theory. We show its efficacy, using stereo-matching as an example.

Original language	English
Pages	708--711
Number of pages	4
Publication status	Published - Aug 2004
Event	Proceedings Intl. Conference on Pattern Recognition (ICPR) - Duration: 1 Aug 2004 → …

Conference

Conference	Proceedings Intl. Conference on Pattern Recognition (ICPR)
Period	1/08/04 → …

Cite this

@conference{9211679711be49b8aa521ddf320d669f,

title = "A Trainable Low-level Feature Detector",

abstract = "We introduce a trainable system that simultaneously filters and classifies low-level features into types specified by the user. The system operates over full colour images, and outputs a vector at each pixel indicating the probability that the pixel belongs to each feature type. We explain how common features such as edge, corner, and ridge can all be detected within a single framework, and how we combine these detectors using simple probability theory. We show its efficacy, using stereo-matching as an example.",

author = "Hall, {P M} and Owen, {M J} and Collomosse, {J P}",

year = "2004",

month = aug,

language = "English",

pages = "708----711",

note = "Proceedings Intl. Conference on Pattern Recognition (ICPR) ; Conference date: 01-08-2004",

}

TY - CONF

T1 - A Trainable Low-level Feature Detector

AU - Hall, P M

AU - Owen, M J

AU - Collomosse, J P

PY - 2004/8

Y1 - 2004/8

N2 - We introduce a trainable system that simultaneously filters and classifies low-level features into types specified by the user. The system operates over full colour images, and outputs a vector at each pixel indicating the probability that the pixel belongs to each feature type. We explain how common features such as edge, corner, and ridge can all be detected within a single framework, and how we combine these detectors using simple probability theory. We show its efficacy, using stereo-matching as an example.

AB - We introduce a trainable system that simultaneously filters and classifies low-level features into types specified by the user. The system operates over full colour images, and outputs a vector at each pixel indicating the probability that the pixel belongs to each feature type. We explain how common features such as edge, corner, and ridge can all be detected within a single framework, and how we combine these detectors using simple probability theory. We show its efficacy, using stereo-matching as an example.

M3 - Paper

SP - 708

EP - 711

T2 - Proceedings Intl. Conference on Pattern Recognition (ICPR)

Y2 - 1 August 2004

ER -

A Trainable Low-level Feature Detector

Abstract

Conference

Fingerprint

Cite this