Hippocampus-heuristic character recognition network for zero-shot learning in Chinese character recognition
作者：
Highlights：
• A novel hippocampus-heuristic character recognition network (HCRN) is proposed for zero/few-shot learning.
• We propose a spatial-radical-feature retrieval method for character recognition.
• HCRN can successfully recognize Chinese characters even with part of their radicals.
• Most of the existed methods need to analyze the structure of each character for recognition, while HCRN doesn’t follow this strategy.
• HCRN achieves state-of-the-art results on each experiment, especially when the training character classes are very few.
摘要
•A novel hippocampus-heuristic character recognition network (HCRN) is proposed for zero/few-shot learning.•We propose a spatial-radical-feature retrieval method for character recognition.•HCRN can successfully recognize Chinese characters even with part of their radicals.•Most of the existed methods need to analyze the structure of each character for recognition, while HCRN doesn’t follow this strategy.•HCRN achieves state-of-the-art results on each experiment, especially when the training character classes are very few.
论文关键词：Chinese character recognition,Hippocampus thinking,Radical analysis,Zero-shot learning,Label embedding
论文评审过程：Received 2 November 2021, Revised 5 May 2022, Accepted 26 May 2022, Available online 27 May 2022, Version of Record 31 May 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.108818
