RZCR: Zero-shot Character Recognition via Radical-based Reasoning
This addresses the issue of unbalanced data distribution in real-world character recognition, particularly for uncommon characters, though it appears incremental as it builds on existing radical-based methods.
The paper tackles the long-tail problem in character recognition by proposing RZCR, a zero-shot framework that uses radical-based reasoning to improve performance on uncommon characters with few training samples, showing promising results on multiple datasets.
The long-tail effect is a common issue that limits the performance of deep learning models on real-world datasets. Character image datasets are also affected by such unbalanced data distribution due to differences in character usage frequency. Thus, current character recognition methods are limited when applied in the real world, especially for the categories in the tail that lack training samples, e.g., uncommon characters. In this paper, we propose a zero-shot character recognition framework via radical-based reasoning, called RZCR, to improve the recognition performance of few-sample character categories in the tail. Specifically, we exploit radicals, the graphical units of characters, by decomposing and reconstructing characters according to orthography. RZCR consists of a visual semantic fusion-based radical information extractor (RIE) and a knowledge graph character reasoner (KGR). RIE aims to recognize candidate radicals and their possible structural relations from character images in parallel. The results are then fed into KGR to recognize the target character by reasoning with a knowledge graph. We validate our method on multiple datasets, and RZCR shows promising experimental results, especially on few-sample character datasets.