Improving Convolutional Neural Network (CNN) architecture (miniVGGNet) with batch normalization and learning rate decay factor for image classification

The image classification is a classical problem of image processing, computer vision, and machine learning. This paper presents an analysis of the performance using Convolutional Neural Network (CNN) for image classifying using deep learning. MiniVGGNet is CNN architecture used in this paper to trai...

Full description

Bibliographic Details
Main Authors: Ismail, Asmida, Ahmad, Siti Anom, Che Soh, Azura, Hassan, Mohd Khair, Harith, Hazreen Haizi
Format: Article
Language:English
Published: UTHM Publisher 2019
Online Access:http://psasir.upm.edu.my/id/eprint/80197/
http://psasir.upm.edu.my/id/eprint/80197/1/Improving%20Convolutional%20Neural%20Network%20%28CNN%29%20architecture%20%28miniVGGNet%29%20with%20Batch%20Normalization%20and%20Learning%20Rate%20Decay%20Factor%20for%20Image%20Classification.pdf
_version_ 1848858854032408576
author Ismail, Asmida
Ahmad, Siti Anom
Che Soh, Azura
Hassan, Mohd Khair
Harith, Hazreen Haizi
author_facet Ismail, Asmida
Ahmad, Siti Anom
Che Soh, Azura
Hassan, Mohd Khair
Harith, Hazreen Haizi
author_sort Ismail, Asmida
building UPM Institutional Repository
collection Online Access
description The image classification is a classical problem of image processing, computer vision, and machine learning. This paper presents an analysis of the performance using Convolutional Neural Network (CNN) for image classifying using deep learning. MiniVGGNet is CNN architecture used in this paper to train a network for image classification, and CIFAR-10 is selected dataset used for this purpose. The performance of the network was improved by hyper parameter tuning techniques using batch normalization and learning rate decay factor. This paper compares the performance of the trained network by adding batch normalization layer and adjusting the value of learning rate decay factor for the network architecture. Based on the experimental results, adding batch normalization layer allow the networks to improve classification accuracy from 80% to 82%. Applying learning rate decay factor will improve classification accuracy to 83% and reduce the effects of overfitting in learning plot. Performance analysis shows that applying hyper parameter tuning can improve the performance of the network and increasing the ability of the model to generalize.
first_indexed 2025-11-15T12:20:03Z
format Article
id upm-80197
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T12:20:03Z
publishDate 2019
publisher UTHM Publisher
recordtype eprints
repository_type Digital Repository
spelling upm-801972020-10-02T00:14:08Z http://psasir.upm.edu.my/id/eprint/80197/ Improving Convolutional Neural Network (CNN) architecture (miniVGGNet) with batch normalization and learning rate decay factor for image classification Ismail, Asmida Ahmad, Siti Anom Che Soh, Azura Hassan, Mohd Khair Harith, Hazreen Haizi The image classification is a classical problem of image processing, computer vision, and machine learning. This paper presents an analysis of the performance using Convolutional Neural Network (CNN) for image classifying using deep learning. MiniVGGNet is CNN architecture used in this paper to train a network for image classification, and CIFAR-10 is selected dataset used for this purpose. The performance of the network was improved by hyper parameter tuning techniques using batch normalization and learning rate decay factor. This paper compares the performance of the trained network by adding batch normalization layer and adjusting the value of learning rate decay factor for the network architecture. Based on the experimental results, adding batch normalization layer allow the networks to improve classification accuracy from 80% to 82%. Applying learning rate decay factor will improve classification accuracy to 83% and reduce the effects of overfitting in learning plot. Performance analysis shows that applying hyper parameter tuning can improve the performance of the network and increasing the ability of the model to generalize. UTHM Publisher 2019 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/80197/1/Improving%20Convolutional%20Neural%20Network%20%28CNN%29%20architecture%20%28miniVGGNet%29%20with%20Batch%20Normalization%20and%20Learning%20Rate%20Decay%20Factor%20for%20Image%20Classification.pdf Ismail, Asmida and Ahmad, Siti Anom and Che Soh, Azura and Hassan, Mohd Khair and Harith, Hazreen Haizi (2019) Improving Convolutional Neural Network (CNN) architecture (miniVGGNet) with batch normalization and learning rate decay factor for image classification. International Journal of Integrated Engineering, 11 (4). pp. 51-59. ISSN 2229-838X; ESSN: 2600-7916 10.30880/ijie.2019.11.04.006
spellingShingle Ismail, Asmida
Ahmad, Siti Anom
Che Soh, Azura
Hassan, Mohd Khair
Harith, Hazreen Haizi
Improving Convolutional Neural Network (CNN) architecture (miniVGGNet) with batch normalization and learning rate decay factor for image classification
title Improving Convolutional Neural Network (CNN) architecture (miniVGGNet) with batch normalization and learning rate decay factor for image classification
title_full Improving Convolutional Neural Network (CNN) architecture (miniVGGNet) with batch normalization and learning rate decay factor for image classification
title_fullStr Improving Convolutional Neural Network (CNN) architecture (miniVGGNet) with batch normalization and learning rate decay factor for image classification
title_full_unstemmed Improving Convolutional Neural Network (CNN) architecture (miniVGGNet) with batch normalization and learning rate decay factor for image classification
title_short Improving Convolutional Neural Network (CNN) architecture (miniVGGNet) with batch normalization and learning rate decay factor for image classification
title_sort improving convolutional neural network (cnn) architecture (minivggnet) with batch normalization and learning rate decay factor for image classification
url http://psasir.upm.edu.my/id/eprint/80197/
http://psasir.upm.edu.my/id/eprint/80197/
http://psasir.upm.edu.my/id/eprint/80197/1/Improving%20Convolutional%20Neural%20Network%20%28CNN%29%20architecture%20%28miniVGGNet%29%20with%20Batch%20Normalization%20and%20Learning%20Rate%20Decay%20Factor%20for%20Image%20Classification.pdf