Automated Grading for Handwritten Answer Sheets using Convolutional Neural Networks

Abstract

Optical Character Recognition (OCR) is an extensive research field in image processing and pattern recognition. Traditional character recognition methods cannot distinguish a character or a word from a scanned image. This paper proposes a system, which is to develop a method that uses a personal computer, a portable scanner and an application program that would automatically correct the handwritten answer sheets. For handwritten character recognition, the scanned images are fed through a machine learning classifier known as the Convolutional Neural Network (CNN). Two CNN models were proposed and trained on 250 images that were collected from students at Prince Mohammad Bin Fahd University. The proposed system will finally output the final score of the student by comparing each classified answer with the correct answer. The experimental results exhibited that the proposed system performed a high testing accuracy of 92.86%. The system can be used by the instructors in several educational institutions to automatically grade the handwritten answer sheets of students effectively.