Open AccessHandwritten recognition of Hiragana and Katakana characters based on template matching algorithm
Author(s) -
Yosep Septiana,
Asri Mulyani,
Dede Kurniadi,
H Hasanudin
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1098/3/032093
Subject(s) - computer science , natural language processing , character (mathematics) , matching (statistics) , kanji , chinese characters , speech recognition , character recognition , artificial intelligence , template matching , image (mathematics) , mathematics , statistics , geometry
Japanese has become one of the most popular foreign languages in Indonesia. From a survey conducted by The Japan Foundation in 2017 shows that Indonesia is the first largest student in Southeast Asia, therefore those interested in learning Japanese are quite popular in Indonesia. One of the things learned in Japanese is about writing Hiragana and Katakana characters, each of which has 46 standard characters. The research aims to implement a template matching algorithm for handwritten recognition of Hiragana and Katakana characters, which can later be implemented in application design for learning Hiragana and Katakana character writing. Through the application of template matching algorithm, the accuracy level of handwritten recognitions pattern matching reaches 89.8%, so the algorithm will be very suitable if implemented for Hiragana and Katakana characters writing learning applications.