METHOD FOR AUTOMATIC COLOR BALANCING IN DIGITAL IMAGES

The present invention provides an automatic color balancing method for digital images by essentially performing adaptive weighting of surface reflectance and illuminant spectra components of the image. The adaptive weighting mechanism is derived from fuzzy logic based inference methods, taking advantage of its ability to perform inferences from data by providing a computational framework for knowledge that is in linguistic form. It also makes it amenable for implementation on hardware because of the commercially available fuzzy logic chips that already exist in real-world systems such as camcorders for image stabilization, washing machines, etc. The present invention enables much more efficient and robust color segmentation that forms core components for several computer vision algorithms.