Classifying cervical cells using a recurrent neural network by building basins of attraction

This paper describes the result of classifying cervical cells employing a novel way of using a Hopfield-style neural network for classification. This method could be used as part of an automated cervical screening system. Rather than storing the exemplars (training elements) as stable points, a connection matrix is determined, using perceptron-type learning, such that the exemplars are placed in basins of attraction. The exemplars from different classes of cells are placed in different basins of attraction, with usually more than one basin per training class. A presented element is then classified by the basin of attraction it falls into. Input to the classification consists of one case of feature vectors derived from the cervical cell images; in another case, input consists of the images themselves. Good results were obtained using this technique.