Parametric and non-parametric techniques for identifying images of F-actin distribution in endothelial cells with applied agonists

This research deals with developing automatic classification algorithms for identifying images of F-actin distribution in endothelial cells with different treatment of agonists. Parametric and non-parametric classification techniques were investigated such as statistical and artificial neural network classifiers. First and second order features were extracted from the images. Among the statistical classification techniques are the Bayes approach and the K-nearest neighbor (K-NN). For the neural network approach, we used the multilayer feedforward and the functional link network. All of these techniques provide adequate results with the neural methods performing with higher accuracy reaching above 97% classification