Methods for Convolutional Sparse Coding and Coupled Feature Learning with Applications to Image Fusion

Thumbnail Image
Files
isbn9789526412672.pdf (9.15 MB)

isbn9789526412672_errata.pdf (88.65 KB)
Journal Title
Journal ISSN
Volume Title
School of Electrical Engineering | Doctoral thesis (article-based) | Defence date: 2023-06-21
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Author
Date
2023
Department
Informaatio- ja tietoliikennetekniikan laitos
Department of Information and Communications Engineering
Major/Subject
Mcode
Degree programme
Language
en
Pages
74 + app. 76
Series
Aalto University publication series DOCTORAL THESES, 70/2023
Abstract
The sparse approximation model, also known as the sparse coding model, represents signals as linear combinations of only a small number of elements (atoms) from a dictionary. This model is used in many applications of signal processing, machine learning, and computer vision. In many tasks, the use of dictionaries adapted to signal domains has led to significant improvements. The process of finding domain-adapted dictionaries is called dictionary learning. Structured sparse approximation and dictionary learning has been successfully used in applications such as image fusion, where it is required to find correlated patterns in multi-measure and multimodal signals. Image fusion is the problem of combining multiple images, for example, acquired using different imaging modalities, into a single, more informative image.  A shift-invariant extension of the standard sparse approximation model that can describe the entire high-dimensional signals is referred to as convolutional sparse coding (CSC). It has been demonstrated in several studies that the CSC model is superior to its standard counterpart in representing natural signals such as audio and images.  A majority of the leading CSC and CDL algorithms are based on the alternating direction method of multipliers (ADMM) and the Fourier transform. There is only one significant difference between these methods, which is in the way they address a convolutional least-squares regression subproblem. In this thesis, we propose a novel solution for this subproblem that improves the computational efficiency of the existing algorithms. Additionally, we present an efficient ADMM-based approximate online CDL algorithm that can be used in applications that require learning large dictionaries over high-dimensional signals. Next, we propose new methods and develop computationally efficient algorithms for learning correlated features (called coupled feature learning (CFL) in this thesis) in multi-measure and multimodal signals based on sparse approximation and dictionary learning. The presented CFL algorithms potentially apply to signal and image processing tasks where a joint analysis of multiple correlated signals (e.g., multimodal images) is essential. We also propose CSC-based extensions and variations of the proposed CFL algorithm. Based on the proposed CFL methods, we develop multimodal image fusion algorithms. Specifically, the learned coupled dictionary atoms, representing correlated visual features, are used to generate unified enhanced images. We address multimodal medical image fusion, infrared and visible-light image fusion, and near-infrared and visible-light image fusion problems. This thesis contains representative experimental results for all proposed algorithms. The effectiveness of the proposed algorithms is demonstrated based on comparisons with state-of-the-art methods.
Description
Supervising professor
Vorobyov, Sergiy A. Prof., Aalto University, Department of Signal Processing and Acoustics, Finland
Keywords
sparse approximation, dictionary learning, convolutional sparse coding, coupled feature learning, image fusion
Other note
Parts
  • [Publication 1]: F. G. Veshki and S. A. Vorobyov. An Efficient Coupled Dictionary Learning Method. IEEE Signal Processing Letters, vol. 26(10), pp. 1441-1445, 2019.
    DOI: 10.1109/LSP.2019.2934045 View at publisher
  • [Publication 2]: F. G. Veshki, N. Ouzir and S. A. Vorobyov. Image Fusion using Joint Sparse Representations and Coupled Dictionary Learning. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, pp. 8344-8348, May 2020.
    DOI: 10.1109/ICASSP40776.2020.9054097 View at publisher
  • [Publication 3]: F. G. Veshki and S. A. Vorobyov. Efficient ADMM-Based Algorithms for Convolutional Sparse Coding. IEEE Signal Processing Letters, vol. 29, pp. 389-393, 2021.
    Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-202203032054
    DOI: 10.1109/LSP.2021.3135196 View at publisher
  • [Publication 4]: F. G. Veshki, N. Ouzir, S. A. Vorobyov and E. Ollila. Multimodal Image Fusion via Coupled Feature Learning. Signal Processing, vol. 200, p. 108637, 2022.
    Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-202208104519
    DOI: 10.1016/j.sigpro.2022.108637 View at publisher
  • [Publication 5]: F. G. Veshki and S. A. Vorobyov. Coupled Feature Learning Via Structured Convolutional Sparse Coding for Multimodal Image Fusion. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, pp. 2500-2504, May 2022.
    Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-202211236580
    DOI: 10.1109/ICASSP43922.2022.9746322 View at publisher
  • [Publication 6]: F. G. Veshki and S. A. Vorobyov. Convolutional Simultaneous Sparse Approximation with Applications to RGB-NIR Image Fusion. In Proceedings of the 56th Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA, November 2022.
    Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-202304052684
    DOI: 10.1109/IEEECONF56349.2022.10052057 View at publisher
  • [Publication 7]: F. G. Veshki and S. A. Vorobyov. Efficient Online Convolutional Dictionary Learning Using Approximate Sparse Components. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes island, Greece, June 2023.
    DOI: 10.1109/ICASSP49357.2023.10096444 View at publisher
  • [Publication 8]: F. G. Veshki and S. A. Vorobyov. An Efficient Approximate Method for Online Convolutional Dictionary Learning. Submitted for publication, 2023
Citation
Permanent link to this item
https://urn.fi/URN:ISBN:978-952-64-1267-2
Collections
[diss] Sähkötekniikan korkeakoulu / ELEC