@article{Liao_Zhang_Wan_Xie_Liang_Lyu_Yao_Bai_2019, title={Scene Text Recognition from Two-Dimensional Perspective}, volume={33}, url={https://ojs.aaai.org/index.php/AAAI/article/view/4895}, DOI={10.1609/aaai.v33i01.33018714}, abstractNote={<p>Inspired by speech recognition, recent state-of-the-art algorithms mostly consider scene text recognition as a sequence prediction problem. Though achieving excellent performance, these methods usually neglect an important fact that text in images are actually distributed in two-dimensional space. It is a nature quite different from that of speech, which is essentially a one-dimensional signal. In principle, directly compressing features of text into a one-dimensional form may lose useful information and introduce extra noise. In this paper, we approach scene text recognition from a two-dimensional perspective. A simple yet effective model, called Character Attention Fully Convolutional Network (CA-FCN), is devised for recognizing the text of arbitrary shapes. Scene text recognition is realized with a semantic segmentation network, where an attention mechanism for characters is adopted. Combined with a word formation module, CA-FCN can simultaneously recognize the script and predict the position of each character. Experiments demonstrate that the proposed algorithm outperforms previous methods on both regular and irregular text datasets. Moreover, it is proven to be more robust to imprecise localizations in the text detection phase, which are very common in practice.</p>}, number={01}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Liao, Minghui and Zhang, Jian and Wan, Zhaoyi and Xie, Fengming and Liang, Jiajun and Lyu, Pengyuan and Yao, Cong and Bai, Xiang}, year={2019}, month={Jul.}, pages={8714-8721} }