Local Fourier features for handwriting digit images classification

Abstract

Multiple choice questions (MCQ) are effective in normative assessment and offline testing is still relevant due to the lack of efficient mass infrastructures and maintenance. For the automatic correction of MCQ paper form and reporting of the grade, it is generally necessary to read and recognize a handwriting digit in a box. This paper focuses on local feature extraction in the frequency domain using Fourier transform. The pre-process begins with the extraction of the fields from the entity map, followed by the application of 2D fast Fourier transform (2DFFT) and the reduction of computed coefficients to obtain the corresponding final local characteristic in the representation. The experimental results of the Modified National Institute of Standards and Technology (MNIST) handwriting digits dataset show that the local characteristics extracted in the frequency domain used as input to a support vector machine (SVM) classifier are efficient in terms of 99.51% accuracy. The proposed system successfully helped in the reporting of all the marks for seven subjects in a class of 98 students during the automatic correction of the MCQ exam papers.