scholarly journals A Novel Handwritten Digit Classification System Based on Convolutional Neural Network Approach

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6273
Author(s):  
Ali Abdullah Yahya ◽  
Jieqing Tan ◽  
Min Hu
Keyword(s):  
Classification Accuracy ◽  
Domain Knowledge ◽  
Data Augmentation ◽  
Additive White Gaussian Noise ◽  
Data Preparation ◽  
Neural Network Approach ◽  
Digit Recognition ◽  
Noticeable Improvement ◽  
Filter Size ◽  
Handwritten Digit

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 σ = 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.

scholarly journals Digit Recognition Based on Specialization, Decomposition and Holistic Processing

2020 ◽  
Vol 2 (3) ◽  
pp. 271-282
Author(s):  
Michael Joseph ◽  
Khaled Elleithy
Keyword(s):  
Neural Network ◽  
Data Augmentation ◽  
High Efficiency ◽  
Valuable Insight ◽  
Digit Recognition ◽  
Lighting Conditions ◽  
Variational Autoencoder ◽  
The Face ◽  
Handwritten Digit ◽  
Holistic Representation

With the introduction of the Convolutional Neural Network (CNN) and other classical algorithms, facial and object recognition have made significant progress. However, in a situation where there are few label examples or the environment is not ideal, such as lighting conditions, orientations, and so on, performance is disappointing. Various methods, such as data augmentation and image registration, have been used in an effort to improve accuracy; nonetheless, performance remains far from human efficiency. Advancement in cognitive science has provided us with valuable insight into how humans achieve high accuracy in identifying and discriminating between different faces and objects. These researches help us understand how the brain uses the features in the face to form a holistic representation and subsequently uses it to discriminate between faces. Our objective and contribution in this paper is to introduce a computational model that leverages these techniques, being used by our brain, to improve robustness and recognition accuracy. The hypothesis is that the biological model, our brain, achieves such high efficiency in face recognition because it is using a two-step process. We therefore postulate that, in the case of a handwritten digit, it will be easier for a learning model to learn invariant features and to generate a holistic representation than to perform classification. The model uses a variational autoencoder to generate holistic representation of handwritten digits and a Neural Network(NN) to classify them. The results obtained in this research show the effectiveness of decomposing the recognition tasks into two specialize sub-tasks, a generator, and a classifier.

scholarly journals A Survey of Handwritten Character Recognition with MNIST and EMNIST

2019 ◽  
Vol 9 (15) ◽  
pp. 3169 ◽  
Author(s):  
Alejandro Baldominos ◽  
Yago Saez ◽  
Pedro Isasi
Keyword(s):  
Neural Networks ◽  
Character Recognition ◽  
Data Augmentation ◽  
State Of The Art ◽  
Handwritten Digit Recognition ◽  
Test Error ◽  
Digit Recognition ◽  
Original Dataset ◽  
Learning Techniques ◽  
Handwritten Digit

This paper summarizes the top state-of-the-art contributions reported on the MNIST dataset for handwritten digit recognition. This dataset has been extensively used to validate novel techniques in computer vision, and in recent years, many authors have explored the performance of convolutional neural networks (CNNs) and other deep learning techniques over this dataset. To the best of our knowledge, this paper is the first exhaustive and updated review of this dataset; there are some online rankings, but they are outdated, and most published papers survey only closely related works, omitting most of the literature. This paper makes a distinction between those works using some kind of data augmentation and works using the original dataset out-of-the-box. Also, works using CNNs are reported separately; as they are becoming the state-of-the-art approach for solving this problem. Nowadays, a significant amount of works have attained a test error rate smaller than 1% on this dataset; which is becoming non-challenging. By mid-2017, a new dataset was introduced: EMNIST, which involves both digits and letters, with a larger amount of data acquired from a database different than MNIST’s. In this paper, EMNIST is explained and some results are surveyed.

scholarly journals Expiry Date Digit Recognition using Convolutional Neural Network

2021 ◽  
Vol 5 (1) ◽  
pp. 85-88
Author(s):  
Tareq Khan
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Classification Accuracy ◽  
Learning Model ◽  
Expiry Date ◽  
Digit Recognition ◽  
Handwritten Digit ◽  
Deep Learning Model

The expiry dates printed on the merchandise have a distinct background, font, alignment, and color in comparison with the available handwritten digit datasets. In this paper, an expiry date dataset is used, and also a convolutional neural network (CNN) model is proposed to recognize expiry dates out of images. This model may be employed together with our previously proposed smart expiry architecture to get an automated notification to the smartphone for the foods which are expiring soon. The suggested deep learning model is tested and has a classification accuracy of 90%.

scholarly journals Handwritten Digit Recognition System

2021 ◽  
pp. 76-85
Author(s):  
Shubham Mendapara ◽  
Krish Pabani ◽  
Yash Paneliya
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Learning Strategies ◽  
Optical Character Recognition ◽  
Handwritten Digit Recognition ◽  
Neural Network Approach ◽  
Data Set ◽  
Digit Recognition ◽  
Handwritten Digit ◽  
Compositional Styles

Recently, handwritten digit recognition has become impressively significant with the escalation of the Artificial Neural Networks (ANN). Apart from this, deep learning has brought a major turnaround in machine learning, which was the main reason it attracted many researchers. We can use it in many applications. The main aim of this article is to use the neural network approach for recognizing handwritten digits. The Convolution Neural Network has become the center of all deep learning strategies. Optical character recognition (OCR) is a part of image processing that leads to excerpting text from images. Recognizing handwritten digits is part of OCR. Recognizing the numbers is an important and remarkable subject. In this way, since the handwritten digits are not of same size, thickness, position, various difficulties are faced in determining the problem of recognizing handwritten digits. The unlikeness and structure of the compositional styles of many entities further influences the example and presence of the numbers. This is the strategy for perceiving and organizing the written characters. Its applications are such as programmed bank checks, health, post offices, for education, etc. In this article, to evaluate CNN's performance, we used the MNIST dataset, which contains 60,000 images of handwritten digits. Achieves 98.85% accuracy for handwritten digit. And where 10% of the total images were used to test the data set.

Sign in / Sign up

Export Citation Format

Share Document