An Automatic Off-Line Short Answer Assessment System Using Novel Hybrid Features
Document Type
Conference Article
Publication Title
2016 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2016
Abstract
To date, paper-based examinations are still in use worldwide on all levels of education levels (e.g. secondary, tertiary levels). However, literature regarding off-line automatic assessment systems employing off-line handwriting recognition is not numerous. This paper proposes an off-line automatic assessment system employing a hybrid feature extraction technique - a newly proposed Modified Direction and Gaussian Grid Feature (MDGGF), along with its enhanced technique. In this study other original feature extraction techniques, together with their enhanced features, were also used for feature extraction technique efficiency comparison purposes. Classifiers, namely artificial neural networks and support vector machines, were selected to be employed in the experiments. Two types of datasets were employed in the experiment for both feature extraction technique accuracy and efficiency comparisons. The best correctly recognised rate of 98.33% with 100% accuracy was obtained when employing the proposed MDGGF to the off-line automatic assessment system.
DOI
10.1109/DICTA.2016.7797004
Publication Date
12-22-2016
Recommended Citation
Suwanwiwat, Hemmaphan; Pal, Umapada; and Blumenstein, Michael, "An Automatic Off-Line Short Answer Assessment System Using Novel Hybrid Features" (2016). Conference Articles. 664.
https://digitalcommons.isical.ac.in/conf-articles/664
