Hippocampus-heuristic character recognition network for zero-shot learning in Chinese character recognition. (October 2022)

• Record Type: Journal Article
• Authors: Huang, Guanjie; Luo, Xiangyu; Wang, Shaowei; Gu, Tianlong; Su, Kaile
• Is Part Of: Pattern recognition. Volume 130(2022)
• Publication Date: 2022-10
• Subjects: Chinese character recognition -- Hippocampus thinking -- Radical analysis -- Zero-shot learning -- Label embedding; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.108818
• Languages: English
• ISSNs: 0031-3203

Abstract

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. Abstract: The recognition of Chinese characters has always been a challenging task due to their huge variety and complex structures. The current radical-based methods fail to recognize Chinese characters without learning all of their radicals in the training stage. To this end, we propose a novel Hippocampus-heuristic Character Recognition Network (HCRN), which can recognize unseen Chinese characters only by training part of radicals. More specifically, the network architecture of HCRN is a new pseudo-siamese network designed by us, which can learn features from pairs of input samples and use them to predict unseen characters. The experimental results on the recognition of printed and handwritten characters show that HCRN is robust and effective on zero/few-shot learning tasks. For the printed characters, the mean accuracy of HCRN outperforms the state-of-the-art approach by 23.93% on recognizing unseen characters. For the handwritten characters, HCRN improves the mean accuracy by 11.25% on recognizing unseen characters.