Edge Detection of Color Image Using Unit-Linking PCNN
PCNN model has the characteristic of similar group neurons releasing pulse synchronously, which is suitable for image segmentation that performs logarithmic transformation on luminance component of color image in order to accord with human visual characteristics. During the segmentation process of R, G, B three components of color images, choosing neuron key parameters by genetic algorithm, controlling iteration by skewness indicators, achieving edge detection of split graphs from R, G, B three components in the model of Unit-Linking PCNN, and getting final results by the strategy of weighted combination. Simulation results show that the approach can embody more contour details of images, and is more self-adaptive.
X. C. Wang et al., "Edge Detection of Color Image Using Unit-Linking PCNN", Applied Mechanics and Materials, Vols. 55-57, pp. 1211-1217, 2011