CLASSIFYING EXPRESSIONS BY CASCADE-CORRELATION NEURAL-NETWORK

The classification of facial expressions by cascade-correlation neural networks [I] is described. A success rate of 100% over the training d ata for each of six categories of emotion - happiness, sadness, anger, surprise, fear and disgust - and of up to 87.5% over the same categor ies for the test data, has been achieved. By using single emotion nets for each category, together with a Net for Resolution, the results re present a 12.5% success rate beyond what was achieved by a single net classifying over ah six emotion categories. Face data in the form of 1 0 hand measurements made on 94 well validated full face photographs [2 ] provided the input data after normalisation. These measures, among o thers, had previously been shown to discriminate between emotions [3].