This paper presents an automatic binarization method for color text areas in images or videos, which is robust to complex background, low resolution or video coding arte- facts. Based on a specific architecture of convolutional neu- ral networks, the proposed system automatically learns how to perform binarization, from a training set of synthesized text images and their corresponding desired binary images, without making any assumptions or using tunable parame- ters. The proposed method is compared to state-of-the-art binarization techniques, with respect to Gaussian noise and contrast variations, demonstrating the robustness and the efficiency of our method. Text recognition experiments on a database of images extracted from video frames and web pages, with two classical OCRs applied on the obtained bi- nary images show a strong enhancement of the recognition rate by more than 40%.