Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN)
Traditional systems of handwriting recognition have relied on handcrafted features and a large amount of prior knowledge. Training an Optical character recognition (OCR) system based on these prerequisites is a challenging task. Research in the handwriting recognition field is focused around deep le...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-06-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/12/3344 |
id |
doaj-b596602515f14c68b86ef59ad9172423 |
---|---|
record_format |
Article |
spelling |
doaj-b596602515f14c68b86ef59ad91724232020-11-25T02:27:06ZengMDPI AGSensors1424-82202020-06-01203344334410.3390/s20123344Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN)Savita Ahlawat0Amit Choudhary1Anand Nayyar2Saurabh Singh3Byungun Yoon4Department of Computer Science and Engineering, Maharaja Surajmal Institute of Technology, New Delhi 110058, IndiaDepartment of Computer Science, Maharaja Surajmal Institute, New Delhi 110058, IndiaGraduate School, Duy Tan University, Da Nang 550000, VietnamDepartment of Industrial & Systems Engineering, Dongguk University, Seoul 04620, KoreaDepartment of Industrial & Systems Engineering, Dongguk University, Seoul 04620, KoreaTraditional systems of handwriting recognition have relied on handcrafted features and a large amount of prior knowledge. Training an Optical character recognition (OCR) system based on these prerequisites is a challenging task. Research in the handwriting recognition field is focused around deep learning techniques and has achieved breakthrough performance in the last few years. Still, the rapid growth in the amount of handwritten data and the availability of massive processing power demands improvement in recognition accuracy and deserves further investigation. Convolutional neural networks (CNNs) are very effective in perceiving the structure of handwritten characters/words in ways that help in automatic extraction of distinct features and make CNN the most suitable approach for solving handwriting recognition problems. Our aim in the proposed work is to explore the various design options like number of layers, stride size, receptive field, kernel size, padding and dilution for CNN-based handwritten digit recognition. In addition, we aim to evaluate various SGD optimization algorithms in improving the performance of handwritten digit recognition. A network’s recognition accuracy increases by incorporating ensemble architecture. Here, our objective is to achieve comparable accuracy by using a pure CNN architecture without ensemble architecture, as ensemble architectures introduce increased computational cost and high testing complexity. Thus, a CNN architecture is proposed in order to achieve accuracy even better than that of ensemble architectures, along with reduced operational complexity and cost. Moreover, we also present an appropriate combination of learning parameters in designing a CNN that leads us to reach a new absolute record in classifying MNIST handwritten digits. We carried out extensive experiments and achieved a recognition accuracy of 99.87% for a MNIST dataset.https://www.mdpi.com/1424-8220/20/12/3344convolutional neural networkshandwritten digit recognitionpre-processingOCR |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Savita Ahlawat Amit Choudhary Anand Nayyar Saurabh Singh Byungun Yoon |
spellingShingle |
Savita Ahlawat Amit Choudhary Anand Nayyar Saurabh Singh Byungun Yoon Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN) Sensors convolutional neural networks handwritten digit recognition pre-processing OCR |
author_facet |
Savita Ahlawat Amit Choudhary Anand Nayyar Saurabh Singh Byungun Yoon |
author_sort |
Savita Ahlawat |
title |
Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN) |
title_short |
Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN) |
title_full |
Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN) |
title_fullStr |
Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN) |
title_full_unstemmed |
Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN) |
title_sort |
improved handwritten digit recognition using convolutional neural networks (cnn) |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2020-06-01 |
description |
Traditional systems of handwriting recognition have relied on handcrafted features and a large amount of prior knowledge. Training an Optical character recognition (OCR) system based on these prerequisites is a challenging task. Research in the handwriting recognition field is focused around deep learning techniques and has achieved breakthrough performance in the last few years. Still, the rapid growth in the amount of handwritten data and the availability of massive processing power demands improvement in recognition accuracy and deserves further investigation. Convolutional neural networks (CNNs) are very effective in perceiving the structure of handwritten characters/words in ways that help in automatic extraction of distinct features and make CNN the most suitable approach for solving handwriting recognition problems. Our aim in the proposed work is to explore the various design options like number of layers, stride size, receptive field, kernel size, padding and dilution for CNN-based handwritten digit recognition. In addition, we aim to evaluate various SGD optimization algorithms in improving the performance of handwritten digit recognition. A network’s recognition accuracy increases by incorporating ensemble architecture. Here, our objective is to achieve comparable accuracy by using a pure CNN architecture without ensemble architecture, as ensemble architectures introduce increased computational cost and high testing complexity. Thus, a CNN architecture is proposed in order to achieve accuracy even better than that of ensemble architectures, along with reduced operational complexity and cost. Moreover, we also present an appropriate combination of learning parameters in designing a CNN that leads us to reach a new absolute record in classifying MNIST handwritten digits. We carried out extensive experiments and achieved a recognition accuracy of 99.87% for a MNIST dataset. |
topic |
convolutional neural networks handwritten digit recognition pre-processing OCR |
url |
https://www.mdpi.com/1424-8220/20/12/3344 |
work_keys_str_mv |
AT savitaahlawat improvedhandwrittendigitrecognitionusingconvolutionalneuralnetworkscnn AT amitchoudhary improvedhandwrittendigitrecognitionusingconvolutionalneuralnetworkscnn AT anandnayyar improvedhandwrittendigitrecognitionusingconvolutionalneuralnetworkscnn AT saurabhsingh improvedhandwrittendigitrecognitionusingconvolutionalneuralnetworkscnn AT byungunyoon improvedhandwrittendigitrecognitionusingconvolutionalneuralnetworkscnn |
_version_ |
1724844258165260288 |