Bubble-Sheet Assessment Checker with Test Grader Using Computer Vision Through Raspberry Pi
Authors:
- 4 August 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 137-142
Abstract
Manual checking of test papers is still one of the most tedious tasks of being an educator. The immediate feedback of these exam results from the teachers enhances the student's learning experience since it also enables the teachers to identify the knowledge gap in the class efficiently. Thus, this study is mainly designed to develop an intelligent bubble-sheet test checker with a scoring system employing computer vision for automated checking using Python. This system requires the examiner to input the student's name and ID number into the system using the touchscreen monitor, then place the bubble sheet properly inside the chamber. The camera button must be pressed to capture the bubble sheet's image and undergo image processing; after a few seconds, the student's score is displayed. Canny edge detection, image segmentation, and inverse warp perspective are some of the image processing techniques involved in this study. To examine the system's accuracy, confusion matrix analysis and paired t-test are used. The confusion matrix analysis assesses the device's correctness in checking each letter on the shaded bubble sheet, which revealed a high accuracy rate of 96.80%. On the other hand, the paired t-test evaluates the accuracy of automated checking versus manual checking, which resulted in a p-value of 0.01.Keywords
This publication has 16 references indexed in Scilit:
- The use of raspberry pi as a portable medical image processingJournal of Physics: Conference Series, 2020
- Integrating Educational Technologies to Augment Learners' Academic AchievementsInternational Journal of Emerging Technologies in Learning (iJET), 2020
- Supervised Machine Learning Approach for Pork Meat Freshness Identification2019
- Detection and Counting of Red Blood Cells in Human Urine using Canny Edge Detection and Circle Hough Transform Algorithms2019
- Inclusion of Vertical Bar in the OMR Sheet for Image-Based Robust and Fast OMR Evaluation Technique Using Mobile Phone Camera2018
- Optimized Methodology Using Multi-Choice Question Tests on Paper From question authoring to grade publishing2018
- Practical Machine Learning with Python2018
- Developing, Analyzing, and Using Distractors for Multiple-Choice Tests in Education: A Comprehensive ReviewReview of Educational Research, 2017
- Iris Recognition using Daugman algorithm on Raspberry Pi2017
- Indoor navigation system based on computer vision using CAMShift and D* algorithm for visually impaired2016