School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China.
Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan, China.
PLoS One. 2022 Aug 29;17(8):e0272601. doi: 10.1371/journal.pone.0272601. eCollection 2022.
Irregular text recognition of natural scene is a challenging task due to large span of character angles and morphological diversity of a word. Recent work first rectifies curved word region, and then employ sequence algorithm to complete the recognition task. However, this strategy largely depends on rectification quality of the text region, and cannot be applied to large difference between tilt angles of character. In this work, a novel anchor-free network structure of rotating character detection is proposed, which includes multiple sub-angle domain branch networks, and the corresponding branch network can be selected adaptively according to character tilt angle. Meanwhile, a curvature Adaptive Text linking method is proposed to connect the discrete strings detected on the two-dimensional plane into words according to people's habits. We achieved state-of-the-art performance on two irregular texts (TotalText, CTW1500), outperforming state-of-the-art by 2.4% and 2.7%, respectively. The experimental results demonstrate the effectiveness of the proposed algorithm.
自然场景中的不规则文本识别是一项具有挑战性的任务，因为字符角度跨度大，单词形态多样。最近的工作首先对弯曲的文字区域进行校正，然后使用序列算法来完成识别任务。然而，这种策略在很大程度上依赖于文本区域的校正质量，并且不能应用于字符倾斜角度的较大差异。在这项工作中，提出了一种新颖的旋转字符检测无锚点网络结构，它包括多个子角度域分支网络，可以根据字符倾斜角度自适应地选择相应的分支网络。同时，提出了一种曲率自适应文本连接方法，根据人们的习惯将在二维平面上检测到的离散字符串连接成单词。我们在两个不规则文本（TotalText、CTW1500）上取得了最先进的性能，分别比最先进的方法提高了 2.4%和 2.7%。实验结果证明了所提出算法的有效性。
