A procedure for the semi-automatic identification of the main protozoa and metazoa species present in the activated sludge of wastewater treatment plants was developed. This procedure was based on both image processing and multivariable statistical methodologies, leading to the use of the image analysis morphological descriptors by discriminant analysis and neural network techniques. The image analysis programwritten in Matlab has proved to be adequate in terms of protozoa and metazoa recognition, as well as for the operating conditions assessment. ; National Council of Scientific and Technological Development of Brazil (CNPq); BIEURAM III ALFA co-operation project (European Commission); Fundação para a Ciência e a Tecnologia (FCT)