Open AccessMachine Replication of Human Perusing using Optical Character Recognition with Tesseract
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.b1079.1292s419
Subject(s) - optical character recognition , character (mathematics) , sort , replication (statistics) , computer science , artificial intelligence , character recognition , natural language processing , information retrieval , computer vision , pattern recognition (psychology) , computer graphics (images) , image (mathematics) , biology , mathematics , geometry , virology
Optical Character Recognition is the machine replication of human perusing. Electronic Conversion of examined pictures where picture can be type composed or printed content. It is executed utilizing Google's open source Optical Character Recognition programming called Tesseract. The OCR accepts picture as the information, gets content from that picture and afterward changes over it into whatever other language that the client needed. This framework can be helpful in different applications like banking, legitimate industry, explorers’ different ventures, and home and office robotization. It for the most part intended for individuals who are unfit to peruse any sort of content archives and to diminish the weight of information passage occupations.[4]