Classification in hyperspectral images by independent component analysis, segmented cross-validation and uncertainty estimates

Abstract

Independent component analysis combined with various strategies for cross-validation, uncertainty estimates by jack-knifing and critical Hotelling’s T2 limits estimation, proposed in this paper, is used for classification purposes in hyperspectral images. To the best of our knowledge, the combined approach of methods used in this paper has not been previously applied to hyperspectral imaging analysis for interpretation and classification in the literature. The data analysis performed here aims to distinguish between four different types of plastics, some of them containing brominated flame retardants, from their near infrared hyperspectral images. The results showed that the method approach used here can be successfully used for unsupervised classification. A comparison of validation approaches, especially leave-one-out cross-validation and regions of interest scheme validation is also evaluated.

Surface analysis insight note. Principal component analysis (PCA) of an X‐ray photoelectron spectroscopy image. The importance of preprocessing

“…As a next step, we recommend that principal component analysis (PCA) be performed. PCA is used in practically every scientific discipline that acquires multivariate signals or large numbers of spectra 33,37–42 . Indeed, PCA is ubiquitous to multivariate analysis, and understanding PCA facilitates an understanding of other factor‐based analysis methods.…”

“…PCA is used in practically every scientific discipline that acquires multivariate signals or large numbers of spectra. 33,[37][38][39][40][41][42] Indeed, PCA is ubiquitous to multivariate analysis, and understanding PCA facilitates an understanding of other factor-based analysis methods. We believe it represents the next level of analysis/ sophistication that can be applied to large XPS data sets.…”