Open AccessJapanese Letter Pattern Recognition Application with Tesseract Engine
Author(s) -
Akhmad Imam Fahrizal,
Ahmad Subhan Yazid,
Shofwatul Uyun
Publication year - 2015
Publication title -
ijid (international journal on informatics for development)/international journal on informatics for development
Language(s) - English
Resource type - Journals
eISSN - 2549-7448
pISSN - 2252-7834
DOI - 10.14421/ijid.2015.04202
Subject(s) - computer science , artificial intelligence , pattern recognition (psychology) , natural language processing , image (mathematics) , computer vision
Digital image processing is a field that is being cultivated by many researchers at this time because it is interesting to apply to various activities, both analysis and production activities. One branch of the digital image is pattern recognition. This study uses Tesseract as a tool to recognize patterns from Hiragana letters. This study was conducted to find out how much Tesseract was able to recognize a Japanese text and handwritten text. This study uses 1 image as training data containing 74 Hiragana letters which are processed through training for each letter. This study has several testing criteria based on font size and resolution to find the best results in pattern recognition. This pattern recognition system is able to do data training and recognize 74 Hiragana letters using the Tesseract Engine. The system can also recognize images with the best success percentage of 98.24% with an image resolution of 200dpi (dots per inch) at size 18. This system can also recognize handwritten images with the best percentage of success of 90% with 200dpi image resolution.