ICE: A Statistical Approach to Identifying Constituents of Biomedical Hyperspectral Images

摘要

A problem of considerable interest in the hyperspectral and chemical imaging communities in recent yearsrnhas been the automated identification and mapping of the constituent materials (“endmembers”) present in arnhyperspectral image. Several of the more important endmember-finding algorithms are discussed and some ofrntheir shortcomings highlighted. A relatively new algorithm, ICE, which attempts to address these shortcomings,rnis introduced. Although ICE was originally developed for exploration applications of airborne hyperspectral data,rnits performance on two biomedical data sets is investigated. Possible future research directions are outlined.