Photomicrographs of 5 species of Cymatocyl~s were digitised, binarised and edited by hand to remove large debris contaminating the images. An artificial neural network (back-propagation of error) was trained to categorise 201 of these specimens after pre-processing the data by Fourier transformation. Of the 299 trials which were carried out, 28% demonstrated better than 70% correct categorisation of the data used in the training sets. The best performing network learned to differentiate the training data set with an error rate of 11 U/;,. The same network gave an error rate of 18% when presented with previously unseen data. The results of training back-propagation of error networks are presented and the performance and limitations are discussed and compared with more classical rnorphometric and clustering techniques for the taxonomic separation of marine plankton. This automatic technique demonstrates the potential of neural network pattern classifiers for addressing the difficult taxonomic task of congeneric classification and also has wider implications for the automatic identification of field samples of marine organisms

Neural network analysis was proposed and evaluated as a method for image analysis of plankton data derived from automatic counting techniques. It was shown that a neural network with 2 layers of weights was capable of learning a large data set by the backward-error propagation method. Significant results were achieved in separating novel images of 2 co-occurring species of Ceratium spp. from the western North Atlantic Ocean.

No abstract

No abstract

No abstract