Statistics Summer Seminar
FRIDAY, July 18th 2014 at 3:10pm, MSB 4208 (Conference Room)
Speaker: Mark Berman, CSIRO Digital Productivity and Services
Title: "Some Statistical Problems in Spectroscopy and Hyperspectral Imaging”
Abstract: Every material has a distinctive spectrum. The spectrum of a material tells us about its chemistry. Hyperspectral images produce a spectrum (represented as several hundred numbers) at each pixel in an image. So hyperspectral images enable us to map variations in chemistry.
The first hyperspectral scanners, built in the 1980’s and 1990’s, were designed for airborne applications, primarily for mineral, environmental and military applications. However, in recent years, hyperspectral microscopes and cameras have been developed and are being used for terrestrial applications in areas such as medical diagnosis, burns analysis and skin cancer, biosecurity, pharmaceuticals, forensics and in agribusiness.
A significant issue in hyperspectral imaging is that the spectra at many pixels in an image are actually mixtures of the spectra of the pure constituents. My main focus over a number of years has been on developing and applying fast and sophisticated algorithms and software for “unmixing” these spectra into their pure constituents, both when the spectra of the pure constituents are known and when they are unknown. This has resulted in two software packages:
- The Spectral Assistant (TSA), which has been incorporated into another CSIRO package, The Spectral Geologist, which is sold commercially; and
- Iterated Constrained Endmembers (ICE), which has yet to be commercialized.
I will give an overview of the algorithms underlying TSA and ICE, and demonstrate their application to some mineral and environmental data sets. Finally, I will discuss extensions of TSA, some complete and some still under development.