Pengenalan Tulisan Tangan Karakter Jepang Menggunakan Library Tesseract Pada Android

Abstract

— Lately, digital image processing in many
developed countries into fields cultivated by many
researchers as attractive to apply to various activities, both
analysis and production activities. One of the branches in
the digital image is pattern recognition. This study uses
Tesseract as a tool to recognize patterns of Japanese letter.
This research was conducted to determine how much
Tesseract is able to recognize an Japanese text and
handwritten text. Common Japanese writing system are
Hiragana and Katagana. The objective of the paper is to
recognize handwritten samples of Japanese using
Tesseract open source Optical Character Recognition
(OCR) engine. Tesseract is trained with data samples of
different persons to generate one user-independent
language model, representing the handwritten Japanese
digit-set.