Paper Info
Title
A Novel Handwritten Digit Classification System Based On Convolutional Neural Network Approach
Abstract
An enormous number of CNN classification algorithms have been proposed in the literature. Nevertheless, in these algorithms, appropriate filter size selection, data preparation, limitations in datasets, and noise have not been taken into consideration. As a consequence, most of the algorithms have failed to make a noticeable improvement in classification accuracy. To address the shortcomings of these algorithms, our paper presents the following contributions: Firstly, after taking the domain knowledge into consideration, the size of the effective receptive field (ERF) is calculated. Calculating the size of the ERF helps us to select a typical filter size which leads to enhancing the classification accuracy of our CNN. Secondly, unnecessary data leads to misleading results and this, in turn, negatively affects classification accuracy. To guarantee the dataset is free from any redundant or irrelevant variables to the target variable, data preparation is applied before implementing the data classification mission. Thirdly, to decrease the errors of training and validation, and avoid the limitation of datasets, data augmentation has been proposed. Fourthly, to simulate the real-world natural influences that can affect image quality, we propose to add an additive white Gaussian noise with sigma = 0.5 to the MNIST dataset. As a result, our CNN algorithm achieves state-of-the-art results in handwritten digit recognition, with a recognition accuracy of 99.98%, and 99.40% with 50% noise.
Year
DOI
Venue
2021
10.3390/s21186273
SENSORS
Keywords
DocType
Volume
data augmentation, Root Mean Square Propagation (RMSprop), batch normalization, MNIST handwritten digit database, receptive field
Journal
21
Issue
ISSN
Citations 
18
1424-8220
0
PageRank 
References 
Authors
0.34
0
3
Name
Order
Citations
PageRank
Ali Abdullah Yahya1182.56
Jieqing Tan213028.88
Min Hu33112.64