In Pulse Coupled Neural Network (PCNN), the conception of time series icon based on neural impulse oscillation realized face recognition by using average time series icon and average Euclidean distance. Simulations showed that the approach is effective and possesses better recognition effect for various faces and complicated expressions.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.