Automatic Evaluation of Exam Papers – A Survey

Abstract

In most of the education systems, a student/learner's efficiency and understanding aretestedbyconducting examinations. Even in this digital era, the test papers are evaluated manually by the examiner. There is no effectual model to evaluateOffline descriptive answers. Handwritten Text Recognition (HTR) can be used to evaluate descriptive answers. HTR is one of the most important research areas in Machine Learning. In recent years researchers have proposed many futuristic models for both online and offline text Recognition. This paper presents a survey of various approaches to evaluatinganswer sheets of objective and descriptive types automatically and the existing state-of-the-art models for offline HTR.