Abstract
Deep Learning has been used in many challenges in the current Big Data era, with great improvements, especially in image classification tasks, helping to boost the potential efficacy in computer vision and signal processing applications. As deep learning techniques develop more and more, automated classification tasks based on convolutional neural networks have integrated many fields and have become indispensable nowadays. Over the past decade, these architectures have become very sophisticated. Although several strategies for deep structures have been used, the frequency domain has not been widely investigated in this field. This research suggests using Fast Fourier convolution layers to perform image classification for skin disorders with a denoising block. The obtained results show that the CNN approach with the FFT considerably decreases the training time compared to a naïve CNN model with convolution. The suggested method was tested using the publicly accessible HAM10000 dataset and achieved an accuracy rate of 88%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Abbreviations
- CNN:
-
Convolutional neural network
- ANN:
-
Artificial neural network
- DNN:
-
Deep Neural Network
- FFT:
-
Fast Fourier Transform
- IFFT:
-
Inverse fast Fourier transform
- HAM1000:
-
Human Against Machine
References
Lee, J.-G., et al.: Deep learning in medical imaging: general overview. Korean J. Radiol. 18(4), 570–584 (2017). https://doi.org/10.3348/kjr.2017.18.4.570
Farsal, W., Anter, S., Ramdani, M.: Deep learning: an overview. In: Proceedings of the 12th International Conference on Intelligent Systems: Theories and Applications, pp. 1–6. New York, NY, USA (2018). https://doi.org/10.1145/3289402.3289538
Abunadi, I., Senan, E.: deep learning and machine learning techniques of diagnosis dermoscopy images for early detection of skin diseases. Electronics 10, 3158 (2021). https://doi.org/10.3390/electronics10243158
Saldanha, N., Pintea, S.L., van Gemert, J.C., Tomen, N.: Frequency learning for structured CNN filters with Gaussian fractional derivatives (2021). https://doi.org/10.48550/arXiv.2111.06660
Vasilache, N., Johnson, J., Mathieu, M., Chintala, S., Piantino, S., LeCun, Y.: Fast Convolutional Nets With fbfft: A GPU Performance Evaluation (2014). https://doi.org/10.48550/arXiv.1412.7580
Lavin. A., S. Gray, S.: Fast algorithms for convolutional neural networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4013–4021. Las Vegas, NV, USA (2016). https://doi.org/10.1109/CVPR.2016.435
Adachi, F., Tomeba, H., Takeda, K.: Introduction of frequency-domain signal processing to broadband single-carrier transmissions in a wireless channel. IEICE Trans. Commun. E92-B(9), 2789–2808 (2009)
Xu, K., Qin, M., Sun, F., Wang, Y.,. Chen, Y.-K., Ren, F.: Learning in the Frequency Domain (2020). https://doi.org/10.48550/arXiv.2002.12416
Qin, Z., Zhang, P., Wu, F., Li, X.: FcaNet: Frequency Channel Attention Networks (2020). https://doi.org/10.48550/arXiv.2012.11879
Stuchi, J., et al.: Improving image classification with frequency domain layers for feature extraction, pp. 1–6 (2017). https://doi.org/10.1109/MLSP.2017.8168168
Wang, H., Wu, X., Huang, Z., Xing, E.: High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks, pp. 8681–8691 (2020). https://doi.org/10.1109/CVPR42600.2020.00871
Cai, M., Li, Y.: Out-of-distribution Detection via Frequency-regularized Generative Models ArXiv (2022). https://doi.org/10.48550/arXiv.2208.09083
Popescu, D., El-khatib, M., Ichim, L.: Skin lesion classification using collective intelligence of multiple neural networks. Sensors 22, 4399 (2022). https://doi.org/10.3390/s22124399
Almaraz Damian, J.A., Ponomaryov, V., Sadovnychiy, S., Castillejos-Fernandez, H.: Melanoma and nevus skin lesion classification using handcraft and deep learning feature fusion via mutual information measures. Entropy 22, 484 (2020). https://doi.org/10.3390/e22040484
Kang, J.J., Srinivasu, P., Gnana Siva Sai, J., Ijaz, M.F., Bhoi, A.K., Kim, W.: Classification of skin disease using deep learning neural networks with MobileNet V2 and LSTM. Sensors 21, 2852 (2021). https://doi.org/10.3390/s21082852
Mohd Sagheer, S.V., George, S.N.: A review on medical image denoising algorithms. Biomed. Signal Process. Control 61, 102036 (2020). https://doi.org/10.1016/j.bspc.2020.102036
Buijs, H., Pomerleau, A., Fournier, M., Tam, W.: Implementation of a fast Fourier transform (FFT) for image processing applications. IEEE Trans. Acoust. Speech Signal Process. 22(6), 420–424 (1974). https://doi.org/10.1109/TASSP.1974.1162620
Chi, L., Jiang, B., Mu, Y.: Fast fourier convolution. In: Advances in Neural Information Processing Systems, vol. 33, pp. 4479–4488 (2020). Accessed 19 Oct 2022
M. Mathieu, M. Henaff, and Y. LeCun, “Fast Training of Convolutional Networks through FFTs.” arXiv, Mar. 06, 2014. doi: https://doi.org/10.48550/arXiv.1312.5851
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90
A survey of transfer learning | Journal of Big Data | Full Text. https://journalofbigdata.springeropen.com/articles/ https://doi.org/10.1186/s40537-016-0043-6Accessed 19 Oct 2022
PyTorch. https://pytorch.org/. Accessed 19 Oct 2022
A Closer Look at Image Convolution. http://www.dspguide.com/ch24/7.htm. Accessed 19 Oct 2022
Abtahi, T., Kulkarni, A., Mohsenin, T.: Accelerating convolutional neural network with FFT on tiny cores, pp. 1–4 (2017). https://doi.org/10.1109/ISCAS.2017.8050588
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Aboulmira, A., Hrimech, H., Lachgar, M. (2023). Evaluating FFT-Based Convolutions on Skin Diseases Dataset. In: Hassanien, A.E., et al. The 3rd International Conference on Artificial Intelligence and Computer Vision (AICV2023), March 5–7, 2023. AICV 2023. Lecture Notes on Data Engineering and Communications Technologies, vol 164. Springer, Cham. https://doi.org/10.1007/978-3-031-27762-7_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-27762-7_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-27761-0
Online ISBN: 978-3-031-27762-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)