迈向零样本字符识别：一个带有部首级标注的黄金标准数据集
Toward Zero-shot Character Recognition: A Gold Standard Dataset with Radical-level Annotations
AI总结：
本文构建了包含部首级和字符级标注的古汉字图像数据集 ACCID，并提出基于拼接合成与图像去噪的适应性增强方法及字符分解重组的零样本 OCR 基线模型，实验验证了其有效性。
摘要：
光学字符识别（OCR）方法已被应用于多种任务，例如街景文本识别和文档分析。近期，零样本 OCR 引起了研究界的兴趣，因为它考虑了具有不平衡数据分布的实际 OCR 场景。然而，目前缺乏用于评估此类采用分治识别策略（即将字符分解为部首）的零样本方法的基准。同时，部首识别作为另一项重要的 OCR 任务，也缺乏用于模型训练的部首级标注。在本文中，我们构建了一个古汉字图像数据集，其中包含部首级和字符级标注，以满足上述方法的需求，该数据集名为 ACCID，其部首级标注包括部首类别、部首位置和结构关系。为了提高 ACCID 的适应性，我们提出了一种基于拼接的合成字符算法来增加训练样本，并应用图像去噪方法来提升图像质量。通过引入字符分解与重组，我们提出了一种零样本 OCR 的基线方法。实验结果从定量和定性两方面证明了 ACCID 和基线模型的有效性。
英文摘要：
Optical character recognition (OCR) methods have been applied to diverse tasks, e.g., street view text recognition and document analysis. Recently, zero-shot OCR has piqued the interest of the research community because it considers a practical OCR scenario with unbalanced data distribution. However, there is a lack of benchmarks for evaluating such zero-shot methods that apply a divide-and-conquer recognition strategy by decomposing characters into radicals. Meanwhile, radical recognition, as another important OCR task, also lacks radical-level annotation for model training. In this paper, we construct an ancient Chinese character image dataset that contains both radical-level and character-level annotations to satisfy the requirements of the above-mentioned methods, namely, ACCID, where radical-level annotations include radical categories, radical locations, and structural relations. To increase the adaptability of ACCID, we propose a splicing-based synthetic character algorithm to augment the training samples and apply an image denoising method to improve the image quality. By introducing character decomposition and recombination, we propose a baseline method for zero-shot OCR. The experimental results demonstrate the validity of ACCID and the baseline model quantitatively and qualitatively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
