Data fusion through fuzzy logic applied to feature extraction from multi-sensory images

A fusion formula based on the measure of fuzziness is developed and tested mathematically against several desirable properties of fusion operators. A fuzzification scheme is established by which different types of input data (images) may be modeled. A defuzzification scheme is carried out to recover crisp data from the combined fuzzy assessment. This approach is implemented and tested with real range and intensity images acquired using an odetics laser scanner. A systematic method for evaluating the results of feature extraction is presented. The goal is to obtain better scene descriptions through a segmentation process of both images. Despite the low resolution of the images and the amount of the noise associated with the acquisition process, the segmented output should be suitable for recognition purposes.<<ETX>>