Automatic cell colony counting by region-growing approach

This paper introduces a new automatic system, of counting based on the elaboration of the digital images of cellular colonies grown on petri dishes. This system is mainly based on the region-growing algorithms for the recognition of the Regions Of Interest (ROI) in the image and Sanger's neural network for the characterization of such regions. Moreover a recognition of the most important filters is made in alternative respect; to region-growing approach. The new Graphics Users Interface is introduced. The better final classification is supplied from a Feed-Forward Neural Net (FF-NN) and compared with the K-Nearest Neighbour (K-NN). The results oil large dataset of ROIs are shown.