Radical analysis network for zero-shot learning in printed Chinese character recognition
This addresses the challenge of recognizing a vast and growing set of Chinese characters for applications in text processing and OCR, offering a novel approach to reduce vocabulary size and handle unseen classes.
The paper tackles the problem of recognizing printed Chinese characters, which have over 20,000 categories and are increasing, by decomposing them into about 500 radicals. It introduces a radical analysis network (RAN) that uses CNNs and RNNs with spatial attention to detect radicals and their spatial structures, enabling zero-shot learning for unseen characters.
Chinese characters have a huge set of character categories, more than 20,000 and the number is still increasing as more and more novel characters continue being created. However, the enormous characters can be decomposed into a compact set of about 500 fundamental and structural radicals. This paper introduces a novel radical analysis network (RAN) to recognize printed Chinese characters by identifying radicals and analyzing two-dimensional spatial structures among them. The proposed RAN first extracts visual features from input by employing convolutional neural networks as an encoder. Then a decoder based on recurrent neural networks is employed, aiming at generating captions of Chinese characters by detecting radicals and two-dimensional structures through a spatial attention mechanism. The manner of treating a Chinese character as a composition of radicals rather than a single character class largely reduces the size of vocabulary and enables RAN to possess the ability of recognizing unseen Chinese character classes, namely zero-shot learning.