Academic Journal
Automation of Examination Evaluation using Matlab-Based Optical Mark Recognition (OMR) System.
| Τίτλος: | Automation of Examination Evaluation using Matlab-Based Optical Mark Recognition (OMR) System. |
|---|---|
| Συγγραφείς: | U., Pradeep Kumar1, Bhogadi, Sai Sowjanya1, Appikonda, Kumar Raju1, Pinninti, Pavani1, Chandaka, Prasanth Kumar1, Tanakala, Tejaswini1 |
| Πηγή: | International Scientific Journal of Engineering & Management. Apr2026, Vol. 5 Issue 4, p1-9. 9p. |
| Θεματικοί όροι: | Image processing, Educational technology, Grading of students, Graphical user interfaces, Multiple choice examinations, Test scoring |
| Reviews & Products: | MatLab (Computer software) |
| Περίληψη: | Multiple Choice Questions (MCQs) are widely used in modern examinations. Traditional Optical Mark Recognition (OMR) systems rely on expensive dedicated hardware or Python/OpenCV implementations that suffer from lighting sensitivity and library dependencies. This paper presents a complete MATLAB-based OMR evaluation system that processes scanned answer sheets through an integrated image-processing pipeline and a user-friendly Graphical User Interface (GUI). The system converts RGB images to grayscale, applies median filtering for noise removal, uses adaptive thresholding and morphological operations for bubble isolation, performs Canny edge detection, and employs region-based pixel density analysis (threshold t = 200, fill ratio > 0.35) to detect filled bubbles. Detected answers are automatically compared with an Excel answer key. The GUI, developed using MATLAB GUIDE, supports image loading, answerkey import, evaluation, and result display (roll number, marks, test ID, and performance remarks). The proposed system achieves 89–94% accuracy on standard OMR sheets, eliminates hardware dependency, and provides a robust, cost-effective solution for educational institutions. [ABSTRACT FROM AUTHOR] |
| Copyright of International Scientific Journal of Engineering & Management is the property of International Scientific Journal of Engineering & Management and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Βάση Δεδομένων: | Business Source Index |
καταχωρήστε σχόλιο πρώτοι!