A Low-Cost OMR Solution for Educational Applications

Deng, Hui; Wang, Rui; Liang, Bo

doi:10.1109/ispa.2008.130

Cited by 33 publications

(24 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [2], the authors presented a system which uses techniques from mathematical morphology, capable of acquiring images from computer cameras to perform automated scoring of a multiple-choice test with highly accurate results. The steps performed by the algorithm were explained in detail and illustrated by its employment in a real case scenario.…”

Section: The Traditional Omrmentioning

confidence: 99%

“…Currently, there are numerous utilization of technologies, whether in the public or private institutions, to shorten the time required for manually marking exams while simultaneously increasing the accuracy and reducing the paper consumption and human errors [1][2][3][4][5]. Printed multiple-choice tests are widely used in education, surveys, or other tests.…”

Section: Introductionmentioning

confidence: 99%

“…OMR [1][2]4,[6][7][8] is a process for the detection and recognition of marks written on paper that is applicable to the responses to multiple-choice tests. This techniques helps reduce the time an assessor must spend, but requires the use of a formatted answer sheet where the response markings are predictably positioned.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Grading of Scanned Multiple Choice Answer Sheets

Muangprathub¹,

Shichim²,

Jaroensuk³

et al. 2018

IJET

View full text Add to dashboard Cite

The motivations for automatic grading of image-based multiple choice answer sheets include significant time and cost reductions. The proposed method supports any pencils or pens used on thin papers, as well as low-cost gridded paper that is easy to use in a typical test. Fourteen different scenarios pertaining to 560 answer sheets were evaluated with automatic reporting of the final grading and its summary. The result shows that an average accuracy of 100% for the cases with nearly complete pencil or pen markings. In the cases with incomplete markings, such as small markings, overflow, and deleted or unclean markings, the accuracies were 62.42%, 93.16%, 99.57%, respectively. The proposed system operates 2.5 times faster than the conventional manual method.

show abstract

Section: The Traditional Omrmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Grading of Scanned Multiple Choice Answer Sheets

Muangprathub¹,

Shichim²,

Jaroensuk³

et al. 2018

IJET

View full text Add to dashboard Cite

show abstract

“…This technology has been widely used in assessing students' multiple-choice tests [1]. Dedicated OMR scanners or image scanners are often used.…”

Section: Introductionmentioning

confidence: 99%

“…Dedicated OMR scanners or image scanners are often used. In the latter case, the image is processed by OMR software with similar efficacy, but slower performance, presenting advantages such as lower cost and the possibility to employ user customizable OMR forms [1,2]. However, providing all hardware and software including the OMR form is not a trivial task.…”

Section: Introductionmentioning

confidence: 99%

A Multiple-Choice Test Recognition System Based on Android and RBFNN

Krisnadi¹,

Mitra²,

Desanti³

et al. 2017

dtcse

View full text Add to dashboard Cite

Abstract. Optical Mark Recognition (OMR) is often used by teachers to help mark students' test in the form of multiple-choice test. This article describes how to build an offline OMR system which run in Android based smartphone. The input is the digital image of student's answer sheet which was taken from smartphone's camera. The system implements image processing techniques to detect and determine not only student's handwritten for his/her ID, name, and form's ID, but also for the answer of each test number. Gradient feature is used as features for the handwritten parts, while pixel density and area are used for the marked parts. Radial Basis Function Neural Network (RBFNN) is implemented to recognize of the students' handwriting. The experiment result shows that the system has successfully identified the answers with 99.69% success rates, but only has 82.28% and 72.25% success rates for digits and uppercase letters recognition respectively.

show abstract