Recognition of Handwritten Japanese Characters Using Ensemble of Convolutional Neural Networks
This work addresses the challenge of digitizing handwritten Japanese characters for applications in data analysis, translation, learning, and cultural preservation, but it is incremental as it builds on existing CNN methods.
The study tackled the problem of recognizing handwritten Japanese Kanji characters by proposing an ensemble of three convolutional neural networks, achieving classification accuracies of 99.4% on MNIST, 96.4% on K-MNIST, 95.0% on K49, and 96.4% on the top 150 classes of the K-Kanji dataset.
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.