Integrated Plagiarism Detection System for Text and Image Based Content in Document

In the world of digital era, images contain textual based information which includes numbers, equations. Paragraphs, symbols, text and other type of data. Many of the mechanisms were brought out for identifying the plagiarism in images as well as text. Identifying the plagiarism in text is available over the internet and many of the tools were available in the market for identifying the plagiarism in the text. Due to this many people to overcome the problem of plagiarism they are using snipping tool and making text as image file and uploading in the document so that the plagiarism of the document is not showing and in the other hand the original author is losing his/her contribution or copyright of their work. Our concept is mainly deals with the identifying plagiarism over the text which is embedded in images. Our work deals with Optical Character Recognition (OCR) mechanism for extracting text in the image files and evaluates the originality of the extracted content and gives original content percentage as well as plagiarized content percentage in the text data and image data separately. By varying the information present in the text from the available resources it is going to conclude the text is original text or plagiarized text. By using this mechanism it makes sure in giving the efficient, authenticity as well as reliability of the image based text plagiarism detection.