A Trainable Low-level Feature Detector

P M Hall, M J Owen, J P Collomosse

Research output: Contribution to conferencePaper

5 Citations (Scopus)

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 languageEnglish
Pages708--711
Number of pages4
Publication statusPublished - Aug 2004
EventProceedings Intl. Conference on Pattern Recognition (ICPR) -
Duration: 1 Aug 2004 → …

Conference

ConferenceProceedings Intl. Conference on Pattern Recognition (ICPR)
Period1/08/04 → …

Fingerprint Dive into the research topics of 'A Trainable Low-level Feature Detector'. Together they form a unique fingerprint.

  • Cite this

    Hall, P. M., Owen, M. J., & Collomosse, J. P. (2004). A Trainable Low-level Feature Detector. 708--711. Paper presented at Proceedings Intl. Conference on Pattern Recognition (ICPR), .