Efficient Handwritten Digit Recognition based on Histogram of Oriented Gradients and SVM
Reza Ebrahimzadeh, Mahdi Jampour · International Journal of Computer Applications · 2014
Automatic Handwritten Digits Recognition (HDR) is the process of interpreting handwritten digits by machines.There are several approaches for handwritten digits recognition.In this paper we have proposed an appearance feature-based approach which process data using Histogram of Oriented Gradients (HOG).HOG is a very efficient feature descriptor for handwritten digits which is stable on illumination variation because it is a gradient-based descriptor.Moreover, linear SVM has been employed as classifier which has better responses than polynomial, RBF and sigmoid kernels.We have analyzed our model on MNIST dataset and 97.25% accuracy rate has been achieved which is comparable with the state of the art.