中国科学院自动化研究所机构知识库

Inspired by the success of DNN models in solving challenging visual problems, this paper studies the task of Chinese Image Charac- ter Recognition (ChnICR) by leveraging DNN model and huge machine simulated training samples. To generate the samples, clean machine born Chinese characters are extracted and are plus with common variations of image characters such as changes in size, front, boldness, shift and complex backgrounds, which in total produces over 28 million character images, covering the vast majority of occurrences of Chinese character in real life images. Based on these samples, a DNN training procedure is employed to learn the appropriate Chinese character recognizer, where the width and depth of DNN, and the volume of samples are empirically discussed. Parallel to this, a holistic Chinese image text recognition sys- tem is developed. Encouraging experimental results on text from 13 TV channels demonstrate the effectiveness of the learned recognizer, from which significant performance gains are observed compared to the base- line system.