Article Sidebar
Published:
Feb 17, 2025Keywords:
Article Details
In accordance with the Copyright Act of 1976, which became effective January 1, 1978, the following statement signed by each author must accompany the manuscript submitted: "I, the undersigned author, transfer all copyright ownership of the manuscript referenced above to the Nigerian Journal of Technological Development, in the event the work is published. I warrant that the article is original, does not infringe upon any copyright or other proprietary right of any third party, is not under consideration by another journal, and has not been published previously. I have reviewed and approve the submitted version of the manuscript and agree to its publication in the Nigerian Journal of Technological Development." A copyright transfer form may be downloaded from the NJTD Website (http://njtd.com.ng/index.php/njtd). Author(s) will be consulted, whenever possible, regarding republication of material. All authors must have access to the data presented and the authors and sponsor (if applicable) must agree to share original data with the editor if requested.
Main Article Content
Automated data extraction and character recognition for handwritten test scripts using image processing and convolutional neural networks
Abstract
Evaluating students through examination scripts in educational environments is crucial, particularly with 'Mastery Feedback' from educators, enhancing student understanding and self-regulation. However, it has remained a hectic exercise requiring some innovative solutions. This study proposes integrating robotics to automate recording and collating marked scripts to reduce the burden on lecturers and improve productivity. Key objectives include developing a data extraction pipeline using methods like Oriented FAST and Rotated BRIEF (O.R.B.) for image alignment and adaptive thresholding for lighting variations. Additionally, a character recognition model using a Single Input Convolutional Neural Network (SICNN) was designed with three preprocessing techniques—binarisation, thinning, and gradient magnitude calculation— tailored to different image requirements. Training on the 'EMNIST by_merge' dataset showed varied validation accuracies, with the gradient input SICNN model achieving the highest at 89.24% overall and the binary input SICNN model excelling with 99.39% on custom scripts. This approach aims to enhance educational administrative processes and efficiency and thus achieve sustainable education.
