Jianfeng Yin and Jeremy R. Cooperstock
Centre for Intelligent Machines
H3A 2A7 Montreal
Due to differing optics, sensor characteristics, and hardware processing employed by video cameras, the resulting colors produced by two cameras can be very different, thus complicating the task of computer vision applications. While various color correction methods exist to deal with this problem, most involve strong assumptions, such as constant illumination, that are, in general, unsatisfied in complex environments. To address the problem of color correction in a less restrictive manner, we propose the use of neural networks, which can easily be trained and which produce excellent results. We compare these results with other methods.