Multi-Column Deep Neural Networks For Offline Handwritten Chinese Character Classification

Multi-Column Deep Neural Networks achieve state of the art recognition rates on Chinese characters from the ICDAR 2011 and 2013 offline handwriting competitions, approaching human accuracy. This performance is the result of averaging 11-layers deep networks with hundreds of maps per layer, trained on raw, distorted images to prevent them from overfiUing. The entire framework runs on a normal desktop computer with a CUDA capable graphics card.