Recognition of Handwritten Japanese Characters Using Ensemble of Convolutional Neural Networks

TL;DR

This paper presents an ensemble of convolutional neural networks for recognizing handwritten Japanese characters, achieving high accuracy across multiple datasets, which advances digital processing of complex Japanese scripts.

Contribution

The study introduces a CNN ensemble approach specifically designed for handwritten Japanese character recognition, demonstrating high accuracy on diverse datasets.

Findings

Achieved over 99% accuracy on MNIST dataset.

Attained up to 96.4% accuracy on K-Kanji dataset.

Proved the effectiveness of CNN ensembles for complex character recognition.

Abstract

The Japanese writing system is complex, with three character types of Hiragana, Katakana, and Kanji. Kanji consists of thousands of unique characters, further adding to the complexity of character identification and literature understanding. Being able to translate handwritten Japanese characters into digital text is useful for data analysis, translation, learning and cultural preservation. In this study, a machine learning approach to analyzing and recognizing handwritten Japanese characters (Kanji) is proposed. The study used an ensemble of three convolutional neural networks (CNNs) for recognizing handwritten Kanji characters and utilized four datasets of MNIST, K-MNIST, Kuzushiji-49 (K49) and the top 150 represented classes in the Kuzushiji-Kanji (K-Kanji) dataset for its performance evaluation. The results indicate feasibility of using proposed CNN-ensemble architecture for recognizing handwritten characters, achieving 99.4%, 96.4%, 95.0% and 96.4% classification accuracy on MNIST, K-MNIS, K49, and K-Kanji datasets respectively.