Farrajota, MiguelRodrigues, J. M. F.du Buf, J. M. H.2015-11-042015-11-042014978-989-758-018-5AUT: JRO00913; DUB00865;http://hdl.handle.net/10400.1/6996Coloured regions can be segregated from each other by using colour-opponent mechanisms, colour contrast, saturation and luminance. Here we address segmentation by using end-stopped cells tuned to colour instead of to colour contrast. Colour information is coded in separate channels. By using multi-scale cortical endstopped cells tuned to colour, keypoint information in all channels is coded and mapped by multi-scale peaks. Unsupervised segmentation is achieved by analysing the branches of these peaks, which yields the best-fitting image regions. Copyright © 2014 SCITEPRESS.engColourSegmentationKeypointClusterMulti-scaleVisual Cortexconference object