Logo image
Open Research University homepage
Surrey researchers Sign in
A Trainable Low-level Feature Detector
Conference presentation

A Trainable Low-level Feature Detector

PM Hall, MJ Owen and JP Collomosse
Proceedings Intl. Conference on Pattern Recognition (ICPR), Vol.1, pp.708-711
23/08/2004–26/08/2004
08/2004

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.

Metrics

Details

Logo image

Usage Policy