A Comprehensive Comparative Experiment of Edge Detection Algorithms for OMR
Abstract
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.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a copyright form (JACTA) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
