通过结构感知提升中文复杂字和低频字识别准确率
SAN: Structure-Aware Network for Complex and Long-tailed Chinese Text Recognition
- 引入部件分支与层级信息，增强模型对汉字结构的感知能力
- 在多个中文数据集上，复杂字与尾部类字符识别率显著提升
- 适合需要高精度中文文本识别的应用场景
在文本识别中，复杂字形和尾部类别始终影响模型性能。针对中文文本识别，缺乏形状感知易导致形近字混淆，而这类字通常为训练集中出现频率较低的尾部类别，模型难以捕捉其形状特征。为此，本文提出一种结构感知网络，利用汉字的层级构成信息提升复杂字识别效果。具体地，设计辅助部件分支，并作为正则项融入基础识别网络，将层级构成信息提炼至特征提取器；进一步提出基于树相似性的加权机制，充分利用层级表示中的深度信息。实验表明，该方法显著提升了复杂字与尾部类别的识别性能，整体表现更优。代码已开源：https://github.com/Levi-ZJY/SAN。
原文摘要 · Abstract (English)
In text recognition, complex glyphs and tail classes have always been factors affecting model performance. Specifically for Chinese text recognition, the lack of shape-awareness can lead to confusion among close complex characters. Since such characters are often tail classes that appear less frequently in the training-set, making it harder for the model to capture its shape information. Hence in this work, we propose a structure-aware network utilizing the hierarchical composition information to improve the recognition performance of complex characters. Implementation-wise, we first propose an auxiliary radical branch and integrate it into the base recognition network as a regularization term, which distills hierarchical composition information into the feature extractor. A Tree-Similarity-based weighting mechanism is then proposed to further utilize the depth information in the hierarchical representation. Experiments demonstrate that the proposed approach can significantly improve the performances of complex characters and tail characters, yielding a better overall performance. Code is available at https://github.com/Levi-ZJY/SAN.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。