UMA METODOLOGIA PARA VALIDAÇÃO FOTOMÉTRICA EM SISTEMAS INTERATIVOS VISUAIS BASEADA EM INTELIGÊNCIA COMPUTACIONAL

This paper presents an automatic methodology for the photometric validation of an automotive internal illumination system. In the methodology, we propose a method for homogeneity descriptors extraction from each region of evaluation. The human visual perception, represented by the user evaluation, is used to classify the regions as non- and homogeneous. Two machine learning algorithms (Artificial Neural Network and Support Vector Machine) are used for region classification based on the classical extracted homogeneity descriptors guided (i.e., supervised) by the user’s perception. Experimental results show that the proposed methodology reach precision above 90% on the classification of non- and homogeneous regions.