Pengenalan Tulisan Tangan Karakter Jepang Menggunakan Library Tesseract Pada Android

Rony Try Haryanto, Reza Mahardityawarman, Kusnaedi Kusnaedi, Dyas Yudi Priyanggodo

Abstract


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.


Full Text:

PDF

Refbacks

  • There are currently no refbacks.