King's College London

Research portal

Contour Detection in Colour Images Using a Neurophysiologically Inspired Model

Research output: Contribution to journalArticlepeer-review

Original languageEnglish
Pages (from-to)1027-1035
Number of pages9
JournalCognitive Computation
Issue number6
Early online date28 Sep 2016
Accepted/In press19 Sep 2016
E-pub ahead of print28 Sep 2016

King's Authors


Background: The predictive coding/biased competition (PC/BC) model of V1 has previously been applied to locate boundaries defined by local discontinuities in intensity within an image. Objective: Here PC/BC is extended to perform contour detection for colour images. Methods The proposed extensions are inspired by neurophysiological data from single neurons in macaque primary visual cortex (V1). Results: The behaviour of this extended model is consistent with the neurophysiological experimental results. Furthermore, when compared to methods used for contour detection in computer vision, the colour PC/BC model of V1 slightly outperforms some recently proposed algorithms which use more cues and/or require a complicated training procedure. Conclusions: The colour PC/BC model of V1 can successfully simulate the responses properties of orientation-selective double-opponent neuron in macaque V1 and has practical applications for contour detection in natural images.

View graph of relations

© 2020 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454