Deep Learning based English Handwritten Character Recognition
Journal: International Journal of Science and Research (IJSR) (Vol.7, No. 4)Publication Date: 2018-04-05
Authors : Somil Gupta; Tanvi Bansal; Manish Kumar Sharma;
Page : 1402-1404
Keywords : Deep Learning; Convolutional Neural Network; Handwriting recognition; SVM;
Abstract
In this paper we propose a convolutional neural network based handwritten character recognition using SVM as an end classifier. The learning model is based on CNN (Convolutional Neural Network) which is used as a feature extraction tool. The proposed method is more efficient than other existing methods and will be more efficient than modifying the CNN with complex architecture. The recognition rate achieved by the proposed method is 93.3 % which is greater than other existing methods. The computation time of training phase is 13.14 sec and that of testing phase is 13.27 sec. The proposed system was validated by 6 validation points. The overall accuracy of system is 93 %
Other Latest Articles
- A Study of Biochemical Constituents of Panchakavya
- Cyber Physical Systems by Using Wireless Sensor Networks
- Protocol for Systematic Review - Association of Visual Performance with Sports Performance in Badminton
- Assessing Pre-service Teachers Conceptual Understanding on Amount of Substance and the Mole in Ghana
- Performance of Earthquake Resistant Reinforced Concrete Building against Blast Loadings
Last modified: 2021-06-28 19:09:26