Reprint

The Future of Hyperspectral Imaging

Edited by
November 2019
220 pages
  • ISBN978-3-03921-822-6 (Paperback)
  • ISBN978-3-03921-823-3 (PDF)

This is a Reprint of the Special Issue The Future of Hyperspectral Imaging that was published in

Computer Science & Mathematics
Engineering
Physical Sciences
Summary

 

This book includes some very recent applications and the newest emerging trends of hyper-spectral imaging (HSI). HSI is a very recent and strange beast, a sort of a melting pot of previous techniques and scientific interests, merging and concentrating the efforts of physicists, chemists, botanists, biologists, and physicians, to mention just a few, as well as experts in data crunching and statistical elaboration. For almost a century, scientific observation, from looking to planets and stars down to our own cells and below, could be divided into two main categories: analyzing objects on the basis of their physical dimension (recording size, position, weight, etc. and their variations) or on how the object emits, reflects, or absorbs part of the electromagnetic spectrum, i.e., spectroscopy. While the two aspects have been obviously entangled, instruments and skills have always been clearly distinct from each other. With HSI now available, this is no longer the case. This instrument can return specimen dimensionalities and spectroscopic properties to any single pixel of your specimen, in a single set of data. HSI modality is ubiquitous and scale-invariant enough to be used to mark terrestrial resources on the basis of a land map obtained from satellite observation (actually, the oldest application of this type) or to understand if the cell you are looking at is cancerous or perfectly healthy. For all these reasons, HSI represents one of the most exciting methodologies of the new millennium.

Format
  • Paperback
License and Copyright
© 2020 by the authors; CC BY license
Keywords
hyperspectral imaging; Raman; fluorescence; sorting; quality control; black polymers; PZT; classification; machine learning; alternating direction method of multipliers; Cramer–Rao lower bound; forward observation model; linear mixture model; maximum likelihood; multiband image fusion; total variation; fingerprints; blood detection; age determination; hyperspectral imaging; lossless compression; multitemporal hyperspectral images; information theoretic analysis; predictive coding; hyperspectral imaging; plant phenotyping; disease detection; spectral tracking; time series; hyperspectral imaging; principal component analysis; oxygen saturation; wound healing; diabetic foot ulcer; Raman spectroscopy; chemical imaging; compressive detection; spatial light modulators (SLM); digital micromirror device (DMD); digital light processor (DLP); optimal binary filters; Chemometrics; multivariate data analysis; compressive sensing; hyperspectral imaging; multiplexing system; liquid crystal; three-dimensional imaging; integral imaging; remote sensing; point target detection; CS-MUSI; hyperspectral; video; imaging; coastal dynamics; moving vehicle imaging; bi-directional reflectance distribution function (BRDF); hemispherical conical reflectance factor (HCRF); stereo imaging; digital elevation model; Virginia Coast Reserve Long Term Ecological Research (VCR LTER); Hyperspectral imaging; painting samples; retouching pigments; watercolours; multivariate analysis; potatoes; sprouting; primordial leaf count; hyperspectral imaging; spectroscopy; fusion; wavelength selection; PLSR; interval partial least squares; deep learning; hyperspectral imaging; neural networks; machine learning; image processing; hyperspectral imaging; medical imaging by HSI; HSI for biology; remote sensing; hyperspectral microscopy; fluorescence hyperspectral imaging; Raman hyperspectral imaging; infrared hyperspectral imaging; statistical methods for HSI; hyperspectral data mining and compression; statistical methods for HSI; hyperspectral data mining and compression