Abstract:Optical character recognition (OCR) is the mechanical or electronic translation of images of hand-written or printed text into machine-editable text [4]. It is performed by optical character readers which are automated electronic systems. OCR may be defined as the process of converting images of machine printed or handwritten numerals, letters, and symbols into a computer- processable format. This study Show the accuracy of the OCR. PyTesseract is the chosen program to assess the accuracy of the Optical character recognition. We used images from different books in order for us to extract text from images. We have also conducted alpha and beta testing to know if we were able to identify if the results will differ if the program was utilized by us or other person. An inconsistent result had been observed while testing the Pytesseract program. Although this program is very easy to use and most efficient, this study is an evidence that OCR is not always 100. Keywords:Optical character recognition, text extraction, artificial intelligence, information extraction
