A neural network approach for RGB to YMCK color conversion

Printing applications require to convert RGB displayable pictures into four printing process components: yellow, magenta, cyan and black. In almost all cases, the RGB colors on the display differ from YMCK printed colors. The YMCK printed colors can be simulated on the RGB display, using specific models for color reproduction on display and printer. In the paper, a neural network method is proposed as an alternative solution for RGB-YMCK color conversion, in order to simulate on RGB display the YMCK printed colors. The Neugebauer model was used to provide the training data for network. The general RGB simulation process of the printed YMCK colors represents a not bidirectional color conversion, so that, the network finds on possible transformation with a certain probability, strongly dependent on the learning data which determines the weights of the neural network.<>