Coloured 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
The paper presents a method for colour image segmentation based on a region growing procedure. The a...
We present a corner-detection algorithm based on a model for end-stopping cells in the visual cortex...
grantor: University of TorontoAn autonomous, hybrid-based segmentation scheme has been dev...
Coloured regions can be segregated from each other by using colour-opponent mechanisms, colour contr...
Coloured regions can be segregated by using colour-opponency mechanisms, colour contrast, saturation...
We present a non-parametric unsupervised colour image segmentation system that is fast and retains s...
A color image segmentation algorithm based on region growing is presented. Each region is characteri...
Figure segregation from its background is one of the important functions of color vision for our vis...
Many biological and artificial neural networks require the parallel extraction of multiple features,...
This paper proposes a new unsupervised approach for colour image segmentation. A hierarchy of imag...
Stimuli outside classical receptive fields have been shown to influence significantly the activities...
Stimuli outside classical receptive fields significantly influence the neurons' activities in primar...
The classical receptive fields of V1 neurons contain only local visual input features. The visual s...
Due to the character of the original source materials and the nature of batch digitization, quality ...
Hierarchical neural networks require the parallel extraction of multiple features. This raises the q...
The paper presents a method for colour image segmentation based on a region growing procedure. The a...
We present a corner-detection algorithm based on a model for end-stopping cells in the visual cortex...
grantor: University of TorontoAn autonomous, hybrid-based segmentation scheme has been dev...
Coloured regions can be segregated from each other by using colour-opponent mechanisms, colour contr...
Coloured regions can be segregated by using colour-opponency mechanisms, colour contrast, saturation...
We present a non-parametric unsupervised colour image segmentation system that is fast and retains s...
A color image segmentation algorithm based on region growing is presented. Each region is characteri...
Figure segregation from its background is one of the important functions of color vision for our vis...
Many biological and artificial neural networks require the parallel extraction of multiple features,...
This paper proposes a new unsupervised approach for colour image segmentation. A hierarchy of imag...
Stimuli outside classical receptive fields have been shown to influence significantly the activities...
Stimuli outside classical receptive fields significantly influence the neurons' activities in primar...
The classical receptive fields of V1 neurons contain only local visual input features. The visual s...
Due to the character of the original source materials and the nature of batch digitization, quality ...
Hierarchical neural networks require the parallel extraction of multiple features. This raises the q...
The paper presents a method for colour image segmentation based on a region growing procedure. The a...
We present a corner-detection algorithm based on a model for end-stopping cells in the visual cortex...
grantor: University of TorontoAn autonomous, hybrid-based segmentation scheme has been dev...