Fuzzy neural system for estimating the color temperature of digitally captured image with fpga implementation

This paper presents a fuzzy neural approach to establish a model for estimation of unknown illuminant, i.e., color temperature, of a digitally captured image based only on the contents of the image. The estimated temperature may be further utilized to perform white balance for the image. The results demonstrate strong improvement of the proposed approach over a previous work. The comparative study also suggests that the proposed method is more adaptable to generic images and varieties of illuminants and scenes than other existing methods do. Hardware implementation of the algorithm based on FPGA is also presented in this work.