Toward Zero-shot Character Recognition: A Gold Standard Dataset with Radical-level Annotations
This addresses the problem of evaluating zero-shot OCR methods for researchers in computer vision, but it is incremental as it focuses on dataset creation and a baseline approach.
The paper tackles the lack of benchmarks for zero-shot optical character recognition (OCR) by constructing ACCID, a dataset with radical-level and character-level annotations for ancient Chinese characters, and proposes a baseline method that achieves validated results quantitatively and qualitatively.
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.