Use neural networks to recognize students' handwritten letters and incorrect symbols

TL;DR

This paper proposes a neural network-based method for recognizing students' handwritten multiple-choice answers, including incorrect symbols and non-standard options, to automate answer correction.

Contribution

It introduces a classification approach that accounts for standard options and non-standard, incorrect symbols, enhancing recognition accuracy in educational settings.

Findings

Effective recognition of handwritten answers including incorrect symbols.

Improved automation in grading processes.

Handling of non-standard answer inputs.

Abstract

Correcting students' multiple-choice answers is a repetitive and mechanical task that can be considered an image multi-classification task. Assuming possible options are 'abcd' and the correct option is one of the four, some students may write incorrect symbols or options that do not exist. In this paper, five classifications were set up - four for possible correct options and one for other incorrect writing. This approach takes into account the possibility of non-standard writing options.