Computational colour constancy based on convolutional neural networks with a cross-level architecture

Computational colour constancy refers to the problem of obtaining reliable illuminant colour so that the image can be rectified to generate a new image under the canonical illumination by illumination estimation. This study researches on convolutional neural networks (CNNs) with cross-level architecture for colour constancy. This new methodology obtains the illumination estimation by combining widely-used AlexNet model with cross-level strategy, in which, the cross-level strategy is upgraded to a more adaptive and intelligent level for colour constancy problem. The proposed method is based on the assumption of uniform illumination on the scene, and the colour constancy is approached as an illumination classification problem on real illuminants by training the authors' cnns. Furthermore, the output of the networks could be directly used for illumination computation of the scene. Finally, the performance of the proposed methodology is verified by comparing with the networks without cross-level architecture or with similar strategies, including multiple paths architecture, multi-scale architecture and ConvNet structure, to guarantee the feasibility and effectiveness. Experimental results on the test datasets indicate that up to around 26% error could be reduced via the proposed methodology for colour constancy.