GARN: A Novel Generative Adversarial Recognition Network for End-to-End Scene Character Recognition

Hao Kong, Dongqi Tang, Xi Meng, Tong Lu

Abstract: Deep neural networks have shown their powerful ability in scene character recognition tasks; however, in real life applications, it is often hard to find a large amount of high-quality scene character images for training these networks. In this paper, we proposed a novel end-to-end network named Generative Adversarial Recognition Networks (GARN) for accurate natural scene character recognition in an end-to-end way. The proposed GARN consists of a generation part and a classification part. For the generation part, the purpose is to produce diverse realistic samples to help the classifier overcome the overfitting problem. While in the classification part, a multinomial classifier is trained along with the generator in the form of a game to achieve better character recognition performance. That is, the proposed GARN has the ability to augment scene character data by its generation part and recognize scene characters by its classification part. It is trained in an adversarial way to improve recognition performance. The experimental results on benchmark datasets and the comparisons with the state-of-the-art methods show the effectiveness of the proposed GARN in scene character recognition.