A novel multi-branch wavelet neural network for sparse representation based object classification. (March 2023)

• Record Type: Journal Article
• Authors: Nguyen, Tan-Sy; Luong, Marie; Kaaniche, Mounir; Ngo, Long H.; Beghdadi, Azeddine
• Is Part Of: Pattern recognition. Volume 135(2023)
• Publication Date: 2023-03
• Subjects: Object classification -- Sparse coding -- Wavelet transform -- Neural networks -- Multi-branch architecture; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.109155
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Novel efficient deep learning based object classification methods are proposed. The proposed methods aim to exploit the advantages of multiscale wavelets, sparse coding as well as neural networks. A multi-branch wavelet neural network architecture is designed. The proposed multi-branch architecture allows us to produce multiple sparse codes at different directional wavelet subbands that are efficiently exploited during the classification stage. Abstract: Recent advances in acquisition and display technologies have led to an enormous amount of visual data, which requires appropriate storage and management tools. One of the fundamental needs is the design of efficient image classification and recognition solutions. In this paper, we propose a wavelet neural network approach for sparse representation-based object classification. The proposed approach aims to exploit the advantages of sparse coding, multi-scale wavelet representation as well as neural networks. More precisely, a wavelet transform is firstly applied to the image datasets. The generated approximation and detail wavelet subbands are then fed into a multi-branch neural network architecture. This architecture produces multiple sparse codes that are efficiently combined during the classification stage. Extensive experiments, carried out on various types of standard object datasets, have shown the efficiency of the proposed method compared to the existing sparse coding and deep learning-based methods.