期刊名称：International Journal of Early Childhood Special Education
电子版ISSN：1308-5581
出版年度：2022
卷号：14
期号：3
页码：5734-5742
DOI：10.9756/INT-JECSE/V14I3.739
语种：English
出版社：International Journal of Early Childhood Special Education
摘要：This study aims to classify images using VGG19 algorithm with high accuracy and comparing it with the CNN algorithm. Materials and methods: A sample size of 80,000 images is taken from the CIFAR-10 dataset and it is divided into a training dataset (n=64000 (80%)) and a test dataset (n=16000 (20%)). The performance of the classification is compared using two groups namely VGG19 and CNN algorithms. Results: The object classification accuracy for VGG19 and CNN are 91.32 % and 88.93 % respectively. The VGG19 provided the best accuracy value compared to the CNN algorithm with a significance of p = 0.002 (p < 0.05). Conclusion: It is observed that the VGG19 algorithm performed significantly better than the CNN algorithm in image classification.
