Exploring local spatial features in hyperspectral images. (21st August 2020)

• Record Type: Journal Article
• Authors: Ahmad, Mohamad; Vitale, Raffaele; Silva, Carolina S.; Ruckebusch, Cyril; Cocchi, Marina
• Is Part Of: Journal of chemometrics. Volume 34:Number 10(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-08-21
• Subjects: gray‐level co‐occurrence matrix -- hyperspectral images -- multivariate image analysis -- spatial features -- wavelet transform; Chemistry -- Mathematics -- Periodicals; Chemistry -- Statistical methods -- Periodicals; 542.85
• DOI: 10.1002/cem.3295
• Languages: English
• ISSNs: 0886-9383

Abstract

Abstract: We propose a methodological framework to extract spatial features in hyperspectral imaging data and establish a link between these features and the spectral regions, capturing the observed structural patterns. The proposed approach consists of five main steps: (i) two‐dimensional stationary wavelet transform (2D‐SWT) is applied to a hyperspectral data cube, decomposing each single‐channel image with a selected wavelet filter up to the maximum decomposition level; (ii) a gray‐level co‐occurrence matrix is calculated for every 2D‐SWT image resulting from stage (i); (iii) distinctive spatial features are determined by computing morphological descriptors from each gray‐level co‐occurrence matrix; (iv) the morphological descriptors are rearranged in a two‐dimensional data array; and (v) this data matrix is subjected to principal component analysis (PCA) for exploring the variability of the aforementioned descriptors across spectral channels. As a result, groups of spectral wavelengths associated to specific spatial features can be pointed out yielding a better understanding and interpretation of the data. In principle, this information can also be further exploited, for example, to improve the separation of pure spectral profiles in a multivariate curve resolution context. Abstract : A new methodological framework is proposed to analyze hyperspectral imaging data, which allows isolating distinctive spatial features and linking these to the spectral regions capturing the observed structural patterns. It combines two‐dimensional Stationary Wavelet Transform and grey‐level co‐occurrence matrix (GLCM) descriptors to determine distinctive spatial features. Principal Component Analysis is then used for exploring the variability of GLCM‐descriptors across spectral channels. As a result, the spectral wavelengths associated to specific spatial features are depicted yielding enhanced data understanding and interpretation.