The color of invisible fluorescent inks do not be seen any color without UV light during printing. In order to avoid naked eye damage and reduce the time of exposure to UV light, the RGB signal of digital imaging equipment will be used to predict the CIE LAB chromaticity. This study uses regression analysis, Multilayer Perceptron learning, and convolutional neural networks for color prediction. Among them, convolutional neural networks can get the most accurate predictions.