The 11th Iranian and the first International Conference on Machine Vision and Image Processing

Improving Persian Digit Recognition byCombining Deep Neural Networks andSVM and Using PCA

Amir.M Mousavi.H, Alireza Bossaghzadeh
The 11th Iranian and the first International Conference on Machine Vision and Image Processing (MVIP 2020)

Abstract

One of the machine vision tasks is optical character recognition (OCR) that researchers in this field are trying to achieve a high performance and accuracy in the classification task. In this paper, we have used a fine tuned deep Neural networks for Hoda dataset, which is the largest dataset for Persian handwritten digit classification, to extract valuable discriminative features. then, these features are fed to a linear support vector machine (SVM) for classification part. In the next experiment, In order to improve the accuracy and computational load, we applied the Principal component analysis (PCA) to reduce the extracted features dimensions then we fed it to SVM. To the best of our knowledge the proposed method was better than other methods in terms of accuracy measure

Keywords: Deep Neural Networks, Computer Vision, VGG16, Data Augmentation, SVM, PCA, Feature Extraction



© 2017-2021 ISMVIP All Rights Reserved