Fashion-MNIST Classification Based on CNN Image Recognition

Zhengliang Chen; Mingrui Lv; Shiqi Tian; Shangyuan Yin

doi:10.54097/hset.v34i.5463

Authors

Zhengliang Chen
Mingrui Lv
Shiqi Tian
Shangyuan Yin

DOI:

https://doi.org/10.54097/hset.v34i.5463

Keywords:

Neural Network, Image classification, Model comparison.

Abstract

Image classification is an important part of Artificial Intelligence (AI) and involves several tasks such as image normalization, image segmentation, feature extraction etc. Convolutional Neural Network (CNN) has been proved to be an effective network in image classification. According to this study, we had used a relatively small dataset named Fashion-MNIST (i.e. 70,000 images, 10 categories) to find out the model that can have a higher accuracy with limited training samples. We have trained three classic CNN models which are DenseNet121, MobileNet, ResNet 50 respectively. After that, we comprehensively measured the performance by several norms that comes from these three different models. Finally, we had a conclusion on which could be the most efficient one in this scenario based on the test results, in order to discovery which models are the most powerful one, and worth training. Human always deal with many types of images, so people need a powerful AI to help them to recognize and categorize these images. After this study, the DenseNet121 is the most powerful model in these three - DenseNet121, MobileNet, ResNet 50, the method to determine this result is that in the whole study we used a method called control variate method, we use the same amount of images, same amount of training times, then compared the final output of these three models, in the end we discovered that the DenseNet121 is the most powerful one.

Downloads

Download data is not yet available.

References

O'Shea K. et al. An introduction to convolutional neural networks [R]. arXiv preprint arXiv:1511.08458 (2015).

Wood T. Convolutional Neural Network [R]. DeepAI, 17 May 2019, https://deepai.org/machine-learning-glossary-and-terms/convolutional-neural-network

Raschka S et al. Python Machine Learning: Machine Learning and Deep Learning with Python, Scikit-Learn, and Tensorflow 2 [R]. Packt, 2019.

Yalçın O G. The Brief History of Convolutional Neural Networks [J]. Medium, Towards Data Science, 24 Feb. 2021,

Sultana F et al. Advancements in image classification using convolutional neural network [C]. 2018 Fourth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN). IEEE, 2018.

LeCun Y. Gradient-Based Learning Applied to Document Recognition [R]. IEEE Xplore, Nov. 1998

Dhillon A et al. Convolutional neural network: a review of models, methodologies and applications to object detection [J]. Progress in Artificial Intelligence 9.2 (2020): 85-112.

Xiao H et al. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms [R]. arXiv preprint arXiv:1708.07747 (2017).

Khan S et al. A guide to convolutional neural networks for computer vision [J]. Synthesis lectures on computer vision8.1 (2018): 1-207.