Boosting Scene Character Recognition by Learning Canonical Forms of Glyphs
arXiv:1907.05577
Abstract
As one of the fundamental problems in document analysis, scene character recognition has attracted considerable interests in recent years. But the problem is still considered to be extremely challenging due to many uncontrollable factors including glyph transformation, blur, noisy background, uneven illumination, etc. In this paper, we propose a novel methodology for boosting scene character recognition by learning canonical forms of glyphs, based on the fact that characters appearing in scene images are all derived from their corresponding canonical forms. Our key observation is that more discriminative features can be learned by solving specially-designed generative tasks compared to traditional classification-based feature learning frameworks. Specifically, we design a GAN-based model to make the learned deep feature of a given scene character be capable of reconstructing corresponding glyphs in a number of standard font styles. In this manner, we obtain deep features for scene characters that are more discriminative in recognition and less sensitive against the above-mentioned factors. Our experiments conducted on several publicly-available databases demonstrate the superiority of our method compared to the state of the art.
arXiv commentAccepted by International Journal on Document Analysis and Recognition (IJDAR), will appear in ICDAR 2019. Code: https://github.com/Actasidiot/CGRN
References in corpus (5)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Focusing Attention: Towards Accurate Text Recognition in Natural Images
- Deep Structured Output Learning for Unconstrained Text Recognition