Catching up with deep learning in spectral imaging

Spectral images can get spatial characteristics of the imaging target as the RGB images do, but also reflect the internal physical structure and chemical composition of a target. Therefore, they are widely applied in remote sensing, medical detection, food inspection, and other fields. Traditional spectral imaging techniques obtain spectral images through scanning, which has a long acquisition time and large system volume. As computational optics develops, researchers tend to make some encodings in the spectral image acquisition process and resort to iterative optimization algorithms for spectral reconstruction. However, such methods also have many burdens on computation, and usually need minutes or even hours for one reconstruction. In recent years, deep learning has shown its power for science and application, and spectral imaging is not an exception. When spectral imaging equips with deep learning, it can make reconstruction within seconds, together with high spectral resolution and compact systems.

 

In a new article published in Light Science & Application, a team of scientists, led by Professor Xiang Hao from Zhejiang University, China and co-workers have reviewed recent developments in deep-learning-empowered spectral imaging. They gave an overview of how deep learning is applied in spectral imaging, as well as fundamental principles and comparisons of state-of-the-art techniques. They also arranged today’s available spectral datasets for the benefit of researchers in the field of spectral imaging & deep learning

 

Making effective categorizations is essential in writing a review article. The authors believe that they have found the desired categorization approach for deep-learning-based spectral imaging. “We group various learned spectral imaging methods into three categories--amplitude-coded, phase-coded and wavelength-coded—based on the basic characteristics of light.”

---

---