Fast image colourisation using the isolines concept

Abstract

Colourisation is the process of adding colour information to monochromatic images and video sequences. Generally, colourised images are visually more attractive and they are advantageous in areas such as medicine, astronomy, microscopy or education, in which the visualisation of image information plays a crucial role. In this paper, we introduce a novel concept of grayscale image colourisation, which is based on the idea of isolines. The algorithm is straightforward, easy to implement, computationally efficient and it allows a very high colourisation quality to be obtained. The proposed approach utilises the distance transform applied to a grayscale digital image. The final colourisation is performed via the weighted blending of scribbled colours. The comparison with similar state-of-the-art colourisation techniques that is presented proves that the method is computationally more efficient while producing outputs that have the same high quality. Additionally, we provide the pseudocode for the easier implementation of the algorithm and show its multidisciplinary applications.

Video Colorization Methods: a Survey

“…This method main advantage is that it does not depend on the number of user scribbles and it is also simple to implement. These two advantages make the method very attractive [4].…”

“…In this subsection, comparison is made between Colorization using Isolines (CUI) [4], Chrominance Blending Colorization (CBC) [1], Colorization using Optimization (CUO) [3], and Distance Transform based Colorization (DTC) [23]. The results of this comparison are shown in Figure-13.…”

“…In this subsection, comparison is made between Colorization Using Optimization (CUO) [3], Colorization Using Edge-oriented (CUE) [21], and Colorization Using Prioritized source (CUP) [4]. From Figures-(14, 15), CUE gives better results than the two other methods.…”