A frequency-domain approach with learnable filters for image classification

• Published in: Applied soft computing 2024-04, Vol.155, p.111443, Article 111443
• Main Authors: Stuchi, José Augusto, Canto, Natalia Gil, Attux, Romis Ribeiro de Faissol, Boccato, Levy
• Format: Article
• Language: English
• Subjects: Deep learning; Fourier analysis; Frequency filtering; Image classification; Machine learning
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2024.111443

Machine learning applied to computer vision and signal processing is achieving results comparable to the human brain due to the great improvements brought by deep neural networks (DNN). The majority of state-of-the-art architectures are DNN-related, but only a few explicitly explore the frequency domain to extract useful information and improve the results. This paper presents a new approach for exploring the Fourier transform of the input images, which is composed of trainable frequency filters that boost discriminative components in the spectrum. Additionally, we propose a cropping procedure to allow the network to learn both global and local spectral features of the image blocks. The proposed method proved to be competitive concerning well-known DNN architectures in the selected experiments, which involved texture classification, cataract detection, and retina image analysis, where there is a noticeable appeal for the frequency domain, with the advantage of being a lightweight model. •A new architecture for neural networks exploring the frequency domain is proposed.•Trainable frequency filters retrieve image discriminative features.•A block division scheme allows extracting local and global spectral features.•A frequency pooling technique reduces the model parameters and training time.•The proposed model reaches competitive results when compared to modern ConvNets.