Hippocampus-heuristic Character Recognition Network for Zero-shot Learning

TL;DR

This paper introduces HCRN, a hippocampus-inspired neural network capable of zero-shot recognition of unseen Chinese characters by learning from a limited set of radicals, significantly outperforming existing methods.

Contribution

The paper proposes a novel pseudo-siamese network architecture inspired by hippocampus thinking for zero-shot Chinese character recognition, enabling recognition of unseen characters with limited training data.

Findings

HCRN accurately predicts 16,330 unseen Chinese characters.

Recognition accuracy improves by 15% over state-of-the-art methods.

HCRN achieves up to 99.9% accuracy on unseen characters.

Abstract

The recognition of Chinese characters has always been a challenging task due to their huge variety and complex structures. The latest research proves that such an enormous character set can be decomposed into a collection of about 500 fundamental Chinese radicals, and based on which this problem can be solved effectively. While with the constant advent of novel Chinese characters, the number of basic radicals is also expanding. The current methods that entirely rely on existing radicals are not flexible for identifying these novel characters and fail to recognize these Chinese characters without learning all of their radicals in the training stage. To this end, this paper proposes a novel Hippocampus-heuristic Character Recognition Network (HCRN), which references the way of hippocampus thinking, and can recognize unseen Chinese characters (namely zero-shot learning) 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 training character samples and use them to predict unseen Chinese characters. The experimental results show that HCRN is robust and effective. It can accurately predict about 16,330 unseen testing Chinese characters relied on only 500 trained Chinese characters. The recognition accuracy of HCRN outperforms the state-of-the-art Chinese radical recognition approach by 15% (from 85.1% to 99.9%) for recognizing unseen Chinese characters.