In this paper an approach based on modelling of recognition error with Artificial Neural Networks is presented to increase face emotion recognition in absence of any pre-processing or enhancement technique for feature extraction. This approach consists of two stages: in the first stage an ANN structure is defined for the recognition task by means of a Genetic Algorithm (Recognition ANN -ReANN). Then this structure is used to perform recognition on a test set Y to estimate classification error

more »

... obabilities. In the second stage an additional ANN is defined to associate these error patterns with correct classification patterns using the same test set (Corrective ANN -CoANN) . The composite ANN system then is tested with a different set Z. In recognition tasks performed with the ReANN it was observed that some emotions were more likely to be incorrectly classified than others. This was further corroborated with perceptual data. With the integrated ANN system (ReANN plus CoANN) it was observed that some of these emotions could be recognised more accurately. In general overall recognition was increased from 75% to 85% with this approach.