Automatic Image Marking Process

Abstract-Efficient evaluation of student programs and timely processing of feedback is a critical challenge for faculty. Despite persistent efforts and significant advances in this field, there is still room for improvement. Therefore, the present study aims to analyse the system of automatic assessment and marking of computer science programming students’ assignments in order to save teachers or lecturers time and effort. This is because the answers are marked automatically and the results returned within a very short period of time. The study develops a statistical framework to relate image keywords to image characteristics based on optical character recognition (OCR) and then provides analysis by comparing the students’ submitted answers with the optimal results. This method is based on Latent Semantic Analysis (LSA), and the experimental results achieve high efficiency and more accuracy by using such a simple yet effective technique in automatic marking.