LODENet: A Holistic Approach to Offline Handwritten Chinese and Japanese Text Line Recognition

Abstract

One of the biggest obstacles in Chinese and Japanese text line recognition is how to present their enormous character sets. The most common solution is to merely choose and represent a small subset of characters using one-hot encoding. However, such an approach is costly to describe huge character sets, and ignores their semantic relationships. Recent studies have attempted to utilize different encoding methods, but they struggle to build a bijection mapping. In this work, we propose a novel encoding method, called LOgographic DEComposition encoding (LODEC), that can efficiently perform a 1-to-1 mapping for all Chinese and Japanese characters. As such, LODEC enables to encode over 21,000 Chinese and Japanese characters by 520 fundamental elements. Moreover, to handle the vast style variety of handwritten texts in the two languages, we propose a novel deep learning (DL) architecture, called LODENet, together with an end-to-end training scheme, that leverages auxiliary ground truths generated by LODEC or other radical-based encoding methods. We systematically performed experiments on both Chinese and Japanese datasets, and found that our approach surpassed the performance of stateof-the-art baselines. Furthermore, empirical evidence shows that our method can gain significantly improvement using synthesized text line images without the need for domain knowledge.

The Challenges of Recognizing Offline Handwritten Chinese: A Technical Review

“…In addition to the character encoding method discussed in [89], Hoang et al [102] developed a new encoding technique called LOgographic DEComposition Encoding (LODEC). It can perform one-to-one mapping of Chinese.…”

Application of machine learning methods to detect and classify Core images using GAN and texture recognition

“…CNN is a Deep Learning algorithm that can take in an image as input, give importance (learnable weights and biases) to various aspects/objects in the image, and distinguish one from the other. CNNs are advanced learning algorithms that can be used for image classification (Wang et al, 2016;Lee and Kwon, 2017;, object detection (Ren et al, 2015;Gidaris and Komodakis, 2015;Abdallah et al, 2022;Tan et al, 2020), image inpainting (Yu et al, 2018b(Yu et al, , 2019Elharrouss et al, 2020;Yu et al, 2019), handwriting and speech recognition (Abdallah et al, 2020;Park et al, 2019;Nassif et al, 2019;Hoang et al, 2021;Toiganbayeva et al, 2021), and image captioning Aneja et al, 2018). The section that follows introduces earlier work in object detection and image inpainting approaches.…”

Recurrent Neural Network Transducer for Japanese and Chinese Offline Handwritten Text Recognition

“…In Chinese and Japanese, a character pattern consists of multiple radicals, and the radical set is much smaller than the character set. Some researchers [26,27] use the relationship between radicals and characters to enhance recognition. They reported the best results in both CASIA [4] and SCUT-EPT datasets.…”