Search:
Computing and Library Services - delivering an inspiring information environment

Optical Character Recognition based approach for automatic Image Marking Process

Masbah, Aeman (2018) Optical Character Recognition based approach for automatic Image Marking Process. Doctoral thesis, University of Huddersfield.

[img]
Preview
PDF - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (4MB) | Preview

Abstract

In today's world, programming teachers perform tedious tasks, which are time consuming; for instance, preparing and marking daily assignments, preparing and marking programming projects, preparing and marking short exams, etc. These tasks distract programming teachers from fulfilling their key role – teaching. Therefore, using automated marking approach with ability to communicate with students is highly desirable. Despite the existing approaches for automated student marking, there is still a need for more improvement. An automated program marking approach is proposed in this study based on a proposal by iMarking®. This approach automates the process of marking and assignments submission and facilitates the communication between teachers and students by designing and implementing a web-based application. In addition, the proposed approach adopts Optical Character Recognition (OCR) to extract the text from images to be evaluated using novel evaluation metrics. The novel evaluation metrics are formulated based on observation and experiment and aim to calculate the matching similarity and mismatching percentage of the submitted student answers when compared with the optimal answers. Evaluation results from a sample of 100 different programming questions show that the proposed approach is efficient in automatically marking the student answers with 100% accuracy. Furthermore, it is found to be time saving – approximately 197 seconds for marking ten questions – which is in line with the objective of creating a more efficient system for teachers.

Item Type: Thesis (Doctoral)
Subjects: L Education > L Education (General)
T Technology > T Technology (General)
Schools: School of Computing and Engineering
School of Computing and Engineering > Centre for Precision Technologies
Depositing User: Andrew Strike
Date Deposited: 19 Nov 2019 09:47
Last Modified: 19 Nov 2019 10:00
URI: http://eprints.hud.ac.uk/id/eprint/35084

Downloads

Downloads per month over past year

Repository Staff Only: item control page

View Item View Item

University of Huddersfield, Queensgate, Huddersfield, HD1 3DH Copyright and Disclaimer All rights reserved ©