Review on Deep Learning Handwritten Digit Recognition using Convolutional Neural Network
Akanksha Gupta1, Ravindra Pratap Narwaria2, Madhav Singh3

1Akanksha Gupta, M.E student from Madhav Institute of Technology and Science, Gwalior, Madhya Pradesh, India.
2Dr. Ravindra Pratap Narwaria, Assistant Professor in MITS, Gwalior, Madhya Pradesh, India.
3Prof. Madhav Singh, Assistant Professor MITS, Gwalior, Madhya Pradesh, India.

Manuscript received on January 19, 2021. | Revised Manuscript received on January 23, 2021. | Manuscript published on January 30, 2021. | PP: 245-247 | Volume-9 Issue-5, January 2021. | Retrieval Number: 100.1/ijrte.E5287019521 | DOI: 10.35940/ijrte.E5287.019521
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: In this digital world, everything including documents, notes is kept in digital form. The requirement of converting these digital documents into processed information is in demand. This process is called as Handwritten digit recognition (HDR). The digital scan document is processed and classified to identify the hand written words into digital text so that it can be used to keep it in the documents format means in computerized font so that everybody can read it properly. In this paper, it is discussed that classifiers like KNN, SVM, CNN are used for HDR. These classifiers are trained with some predefined dataset and then used to process any digital scan document into computer document format. The scanned document is passed through four different stages for recognition where image is pre-processed, segmented and then recognized by classifier. MNIST dataset is used for training purpose. Complete CNN classifier is discussed in this paper. It is found that CNN is very accurate for HDR but still there is a scope to improve the performance in terms of accuracy, complexity and timing. 
Keywords: Handwritten digit recognition (HDR),Deep learning, Convolutional Neural Networking (CNN),Artificial Neural Network (ANN), Object Character Recognition (OCR), Modified National Institute of Standards and Technology (MNIST), SVM (Support Vector Machine),KNN (K nearest Neighbors), Rectified Linear Unit(ReLU), NN (Neural Networks).