Analisis Teks Bahasa Indonesia Dan Inggris Dari Sebuah Citra Menggunakan Pengolahan Citra Digital

Abstract

The purpose of this research is to analyze Indonesian text and English text from images using digital image processing. The method used in this research is an experimental method such as: literature review , identification problems, hypotheses, analyzing materials, designing programs, conducting tests and drawing conclusions. The result of this research is to detect the text contained in the image. This research result a digital image processing program in text that is containing from an image that has text in it, using input or input in form of a character image. The image that will be recognized into text with Tesseract OCR and output the text detected by the program. This program can show the level of accuracy to recognize characters and words. It conducted kind of testing on 8 images use several of text characters on it. In this case, the system can recognize characters on the text form, with an average accuracy 96% of the test data taken on images sourced from the internet. According to the testing results, this level of accuracy indicates that this application is quite accurate and efficient in identification the image of certain word or text character.