Fourier-Based Image Classification Using CNN

Year 2024, Volume: 5 Issue: 1, 92 - 101, 21.06.2024

Göktuğ Erdem Dağı , Erhan Gökçay , Hakan Tora

https://doi.org/10.53525/jster.1501920

Abstract

Recently, Convolutional Neural Networks (CNNs) have achieved remarkable success in
computer vision, image processing and image processing tasks. Traditional CNN models
work directly with spatial domain images. On the other hand, images obtained with Fast
Fourier Transform (FFT) represent the Frequency domain and provide an advantage in
computational cost by reducing potential calculation complexity. This study uses FFT
converted images as input to the CNN algorithm to increase image classification and
recognition accuracy and investigates the effects of this. The study begins with a
comprehensive review of the foundations and features of FFT. It assumes that by
converting the input images from the Spatial domain to the Frequency domain, the input
image can be learned more efficiently and better results can be achieved in terms of
performance by studying the most important features in the Frequency domain. To evaluate
the effectiveness of this assumption, CIFAR-10, MNIST-Digits and MNIST-Fashion
datasets were used. As a result, it has been shown that FFT-based preprocessing can
improve classification accuracy, especially in cases where the datasets contain
high-frequency noise, and it has shown different results in different datasets. Therefore, it
is thought that the effect of FFT preprocessing varies depending on the datasets.

Keywords

Machine Learning, Image Classification, Frequency Domain, Deep Learning

References

• [1] S. Russell and P. Norvig, "Artificial Intelligence: A Modern Approach," 3rd ed., Prentice Hall, Upper Saddle River, NJ, USA, 2020.
• [2] I. Goodfellow, Y. Bengio, and A. Courville, "Deep Learning," MIT Press, Cambridge, MA, USA, 2016.
• [3] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," in Advances in Neural Information Processing Systems 25, 2012, pp. 1097-1105.
• [4] K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2015, pp. 770-778.
• [5] C. Szegedy et al., "Going Deeper with Convolutions," in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2015, pp. 1-9.
• [6] K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition," in Proc. Int. Conf. Learning Representations, 2014.
• [7] V. Mnih et al., "Playing Atari with Deep Reinforcement Learning," in Advances in Neural Information Processing Systems 27, 2013, pp. 1-9.
• [8] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding," in Proc. NAACL-HLT, 2018, pp. 4171-4186.
• [9] I. Goodfellow et al., "Generative Adversarial Nets," in Advances in Neural Information Processing Systems 27, 2014, pp. 2672-2680.
• [10] A. Vaswani et al., "Attention is All You Need," in Advances in Neural Information Processing Systems 30, 2017, pp. 5998-6008.
• [11] R. Girshick, J. Donahue, T. Darrell, and J. Malik, "R-CNN: Regions with Convolutional Neural Network Features," in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2013, pp. 580-587.
• [12] Akwasi Darkwah Akwaboah, "Implementation of Convolutional Neural Networks for CIFAR-10 Image Classification," 2019.
• [13] Ajala Sunday Adeyinka, "Convolutional Neural Network Implementation for Classification using CIFAR-10," ResearchGate, 2023.
• [14] Hengyue Pan, "Learning Convolutional Neural Networks in Frequency Domain," ResearchGate, 2023.
• [15] S. Tötterström, "Frequency Domain Image Classification with Convolutional Neural Networks," Bachelor’s Thesis, Tampere University, 2023.
• [16] Stuchi, J. A., Canto, N. G., de Faissol Attux, R. R., & Boccato, L. (2024). A frequency-domain approach with learnable filters for image classification. Applied Soft Computing, 155, 111443.