Handwritten Short Answer Evaluation System (HSAES)

This paper presents the design and implementation of an automated evaluation system for short answers. Handwritten Short Answer Evaluation System (HSAES) is an automated short answer evaluation system that is capable of identifying the texts in answer papers and evaluates marks for each short answer based on previous knowledge acquired by the model. Although many essay evaluation systems are available, short answer grading is still a big problem. In the proposed system, Optical Character Recognition tools are used to extract the handwritten texts. Natural Language Processing is used to extract the keywords from human evaluated sample dataset of handwritten answer papers and answer key. The proposed model evaluates scores based on cosine sentence similarity measures. Each sentence in the evaluated answer paper carries their corresponding mark. The developed model can be used to evaluate the marks of the unscored short answers.