Mark B. Batomalaque, Chella May R. Camacho, Maria Jewella P. Dalida, Jen Aldwayne B. Delmo, Vol. 1, No. 2, pp. 1-9, Jun. 2019
10.22662/IJASC.2019.1.2.001, Full Text:
Keywords: Convolutional Neural Network (CNN), image processing, Optical Character Recognition (OCR), Plagiarism

Abstract

Background/Objectives: The IMAGE TO TEXT CONVERSION TECHNIQUE FOR ANTI-PLAGIARISM SYSTEM is a design project on how the Optical Character Recognition will be utilized in order to extract text from images that can be used to increase the accuracy rate of an anti-plagiarism checker. It also highlights the integration of Convolutional Neural Network and its effect in the result of the conversion. Methods/Statistical analysis: Optical Character Recognition is a technology that recognizes text within an image. It is commonly used to recognize text in scanned documents, but it serves many other purposes as well. While Convolutional Neural network is a category of neural networks that have been proven very effective in performing image recognition and classification. The main objective of the study is to design a software that will convert images of text into plain editable text. The study aims to use a specific algorithm to extract useful information from the images. Findings: It will integrate the two algorithm, convolutional neural network and optical character recognition technology in order to develop a software. The input of the software is a document in .docx format and will generate an output in the same format. Improvements/Applications: This software will be an aid to the existing anti-plagiarism checkers to generate a more thorough and better plagiarism check.

Statistics
Cite this article