Improvement of activity level detection in dynamic speckle patterns with fuzzy logic operators

Abstract

In this work, the design of a multi-descriptor model is proposed to improve the identification of activity levels in dynamic laser speckle (DLS) image sequences. Fuzzy predicates evaluated with operators of different logic systems were used. The model considers both temporal and spatial effects of the DLS phenomenon. Experiments were carried out to characterize the drying times of a sample painted with water-based paint, illuminated with a coherent light, whose image sequences were captured with a CCD camera. To assess the improvement of the proposed model with respect to single descriptors, the Kruskal-Wallis test and the silhouette index were used. The compensatory logic operators achieved the best results to improve the discrimination of the activity levels, according to the different drying times in the dynamic laser speckle sequences.