Abstract

Calibration models developed from hyperspectral imaging data may be applied at the pixel level to generate prediction maps that estimate the spatial distribution of components in a sample. Such prediction maps facilitate direct visual interpretation of model performance, and performance indicators can be extracted from them. These maps can be used as a tool to evaluate calibration models developed on hyperspectral imaging data. This paper presents a method for calibration model evaluation based on information obtained from prediction maps and demonstrates its usefulness for preventing overfitting. Partial least-squares regression was used for model calibration in this study, although in principle the proposed method may be used to evaluate other multivariate calibration methods, e.g. ridge regression and principal-components regression.

© 2014 IM Publications LLP

Hyperspectral face recognition using improved inter-channel alignment based on qualitative prediction models

Woon Cho, Jinbeum Jang, Andreas Koschan, Mongi A. Abidi, and Joonki Paik
Opt. Express 24(24) 27637-27662 (2016)

Prediction model of combustion characteristics of methane-air using hyperspectral imaging

Yan Wang, Weijie Zhao, Baorui Wang, and Yue Wang
Appl. Opt. 61(7) D75-D84 (2022)

Lookup-table-based inverse model for mapping oxygen concentration of cutaneous microvessels using hyperspectral imaging

Wei Feng, Rui Shi, Chao Zhang, Tingting Yu, and Dan Zhu
Opt. Express 25(4) 3481-3495 (2017)

Algorithm for mapping cutaneous tissue oxygen concentration using hyperspectral imaging

Sorin Miclos, Sorin Viorel Parasca, Mihaela Antonina Calin, Dan Savastru, and Dragos Manea
Biomed. Opt. Express 6(9) 3420-3430 (2015)

Spatial mapping of proteoglycan content in articular cartilage using near-infrared (NIR) spectroscopy

Isaac O. Afara, Hayley Moody, Sanjleena Singh, Indira Prasadam, and Adekunle Oloyede
Biomed. Opt. Express 6(1) 144-154 (2015)