Automatic colourization of grayscale images based on tensor decomposition

In this paper a colourizing technique based on some tensor properties is proposed. Toward this goal, it is clarified that tensor decomposition possesses the ability of extracting and gathering overall colour information. The methodology considers a grayscale pixel as a balanced vector in RGB colour space. Any deviation to unbalance the colour coordinates means adding colour information to the initial pixel. For finding the appropriate direction of deviation, the proposed technique uses tensor decomposition to extract colour information from a block divided exemplar colour image called reference. Then apply this direction to the best matched block of the grayscale image based on a similarity criterion while its basic structure is preserved. Finally by retrieving from tensor space into spatial domain the conversion is fulfilled. The similarity criteria for block matching and the plausibility of the system output are the most challenging problems. Both images blocks are considered as 3D tensors and Tucker3 with its unique properties is utilized for transferring the colour information. The novelty, simplicity, accuracy, and the conversion speed are some parameters which are introduced and developed by the proposed algorithm. This approach proves that in comparison with spatial or frequency domain, transforming the colour information into tensor space make it more clear and give us better ability of rendering. The results show that the proposed algorithm is able to present the average structural similarity up to 94%.