Efficient Object Extraction Using Fuzzy Cardinality Based Thresholding, Hopfield Network

An efficient technique that integrates the advantages of both fuzzy theory and Hopfield type neural network for object extraction from noisy background is proposed in this article. In the initial phase of the proposed technique, a fuzzy contrast enhancement of the input noisy object scene is carried out. Subsequently, the object scene is thresholded based on its fuzzy cardinality values to generate a smaller region of interest (ROI). Finally, a Hopfield network is used in the ROI to extract the object from the noisy background. Since the estimated ROI is lesser in size than the entire object scene, the Hopfield network required for the object extraction has a smaller network configuration. This in turn makes the object extraction process more efficient rather than the conventional approach where a fully connected network, with number of nodes equal to the number of pixels in the object scene, is used.