A Comprehensive Comparative Experiment of Edge Detection Algorithms for OMR

  • Zahriah Sahri Universiti Teknikal Malaysia Melaka
  • Zuraini Othman
  • Fauziah Kasmin
  • Halizah Basiron


Optical mark reading (OMR) sheets are used widely to key in answers to multiple-choice questions. Many studies have proposed automated OMR grading systems using the web or mobile devices which capture the OMR images. These captured images go through a few image processing steps to display the grades. Edge detection is one of the steps. This study compares different established edge detection algorithms to detect edges of interest in OMR answer sheets such as bubbles or rectangles containing the bubbles. The compared algorithms are Sobel, Roberts, Prewitt, Canny, and Laplacian of Gaussian (LoG). The experimental results show that LoG has accurately detected the edges in OMR images while Sobel is the least effective. Prewitt and Canny deliver almost similar performances, and Roberts falls second worst to Sobel.

Author Biography

Zahriah Sahri, Universiti Teknikal Malaysia Melaka

Fault Diagnosis of power transformer, feature selection, AI classification, data imputation, Genetic Algorithm, Suport Vector Machine

How to Cite
Sahri, Z., Othman, Z., Kasmin, F., & Basiron, H. (2022). A Comprehensive Comparative Experiment of Edge Detection Algorithms for OMR. Journal of Advanced Computing Technology and Application (JACTA), 4(1). Retrieved from https://jacta.utem.edu.my/jacta/article/view/5245