Automated Colorization of Segmented Images Based on Color Harmony

We propose in this paper an automated colorization of segmented images based on a color harmony rule defined by Itten called the contrast of proportion. Artists create an image drawing a sketch and filling its regions following harmony rules. The most significant regions are generally filled first because of their meaning. Then the other regions are filled depending on the previous colors. Our model is able to process images composed of totally blank or partially filled regions. The user defines sectors representing colors on the chromatic hue wheel and may redefine each color proportion. Then a set of colors is selected to compute the desired harmony. To proportionally colorize an image, already existing colors can be taken into account or the harmony can be applied only to blank regions. Each region is filled with only one color and cannot be divided. Thus, exact proportion contrast colorization of segmented images is a difficult algorithmic problem. In order to solve this problem we use different strategies and propose different methods to fill the regions. If they exist, exact solutions are proposed, otherwise three different approximation methods are used to determine combinations of colors-regions close to the defined proportions. Once the image is processed, the user can adapt hue (in the chosen sector), saturation and value of each region to enhance the result. Our results show that our model is flexible and well designed to help artists, illustrators, comics creators or any other user to automatically colorize (partially or totally) their images.

[1]  Lynda Hardman,et al.  Colour Picking-the Pecking Order of Form and Function , 2003 .

[2]  Tien-Tsin Wong,et al.  Manga colorization , 2006, ACM Trans. Graph..

[3]  Walter C. Granville,et al.  Colorimetric Specification of the Color Harmony Manual from Spectrophotometric Measurements , 1944 .

[4]  W. Marsden.  I and J , 2012 .

[5]  Niloy J. Mitra,et al.  Color Harmonization for Videos , 2008, 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing.

[6]  Daniel Cohen-Or,et al.  Color harmonization , 2006, ACM Trans. Graph..

[7]  R. Stephenson.  A and V , 1962, The British journal of ophthalmology.

[8]  L. Ou,et al.  A colour harmony model for two-colour combinations , 2006 .

[9]  M. Lagoudakis.  The 0 – 1 Knapsack Problem An Introductory Survey , 1996 .

[10]  Abderrahim Elmoataz,et al.  Nonlocal graph regularization for image colorization , 2008, 2008 19th International Conference on Pattern Recognition.

[11]  Johannes Itten,et al.  Kunst der Farbe , 1983 .

[12]  Eugène Chevreul,et al.  De la loi du contraste simultané des couleurs et de l'assortiment des objets colorés , 1839 .

[13]  Vincent Boyer,et al.  Harmonic colorization using proportion contrast , 2010, AFRIGRAPH '10.

[14]  James Clerk Maxwell,et al.  On the theory of compound colours, and the relations of the colours of the spectrum , 1860, Proceedings of the Royal Society of London.

[15]  H. Helmholtz.  LXXXI. On the theory of compound colours , 1852 .

[16]  Jirí Zára,et al.  Unsupervised colorization of black-and-white cartoons , 2004, NPAR '04.

[17]  Jean-Noël Vittaut,et al.  Segmented Images Colorization Using Harmony , 2010, 2010 Sixth International Conference on Signal-Image Technology and Internet Based Systems.

[18]  Phil M. Henry,et al.  Colour Harmony , 2007 .