Optimisation and evaluation of hyperspectral imaging system using machine learning algorithm

Gajendra Suthar, Jung Y. Huang, Santhosh Chidangil

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Hyperspectral imaging (HSI), also called imaging spectrometer, originated from remote sensing. Hyperspectral imaging is an emerging imaging modality for medical applications, especially in disease diagnosis and image-guided surgery. HSI acquires a three-dimensional dataset called hypercube, with two spatial dimensions and one spectral dimension. Spatially resolved spectral imaging obtained by HSI provides diagnostic information about the objects physiology, morphology, and composition. The present work involves testing and evaluating the performance of the hyperspectral imaging system. The methodology involved manually taking reflectance of the object in many images or scan of the object. The object used for the evaluation of the system was cabbage and tomato. The data is further converted to the required format and the analysis is done using machine learning algorithm. The machine learning algorithms applied were able to distinguish between the object present in the hypercube obtain by the scan. It was concluded from the results that system was working as expected. This was observed by the different spectra obtained by using the machine-learning algorithm.

Original languageEnglish
Title of host publicationEmerging Imaging and Sensing Technologies for Security and Defence II
EditorsGerald S. Buller, Keith L. Lewis, Richard C. Hollins, Robert A. Lamb
PublisherSPIE
Volume10438
ISBN (Electronic)9781510613409
DOIs
Publication statusPublished - 01-01-2017
EventEmerging Imaging and Sensing Technologies for Security and Defence II 2017 - Warsaw, Poland
Duration: 13-09-201714-09-2017

Conference

ConferenceEmerging Imaging and Sensing Technologies for Security and Defence II 2017
CountryPoland
CityWarsaw
Period13-09-1714-09-17

Fingerprint

Hyperspectral Imaging
machine learning
Imaging System
Imaging systems
Learning algorithms
Learning systems
Learning Algorithm
Machine Learning
optimization
Optimization
evaluation
Evaluation
tomatoes
physiology
Hypercube
Imaging techniques
imaging spectrometers
surgery
format
remote sensing

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Suthar, G., Huang, J. Y., & Chidangil, S. (2017). Optimisation and evaluation of hyperspectral imaging system using machine learning algorithm. In G. S. Buller, K. L. Lewis, R. C. Hollins, & R. A. Lamb (Eds.), Emerging Imaging and Sensing Technologies for Security and Defence II (Vol. 10438). [104380L] SPIE. https://doi.org/10.1117/12.2296863
Suthar, Gajendra ; Huang, Jung Y. ; Chidangil, Santhosh. / Optimisation and evaluation of hyperspectral imaging system using machine learning algorithm. Emerging Imaging and Sensing Technologies for Security and Defence II. editor / Gerald S. Buller ; Keith L. Lewis ; Richard C. Hollins ; Robert A. Lamb. Vol. 10438 SPIE, 2017.
@inproceedings{bd65e7a335884419b9602d530798a4de,
title = "Optimisation and evaluation of hyperspectral imaging system using machine learning algorithm",
abstract = "Hyperspectral imaging (HSI), also called imaging spectrometer, originated from remote sensing. Hyperspectral imaging is an emerging imaging modality for medical applications, especially in disease diagnosis and image-guided surgery. HSI acquires a three-dimensional dataset called hypercube, with two spatial dimensions and one spectral dimension. Spatially resolved spectral imaging obtained by HSI provides diagnostic information about the objects physiology, morphology, and composition. The present work involves testing and evaluating the performance of the hyperspectral imaging system. The methodology involved manually taking reflectance of the object in many images or scan of the object. The object used for the evaluation of the system was cabbage and tomato. The data is further converted to the required format and the analysis is done using machine learning algorithm. The machine learning algorithms applied were able to distinguish between the object present in the hypercube obtain by the scan. It was concluded from the results that system was working as expected. This was observed by the different spectra obtained by using the machine-learning algorithm.",
author = "Gajendra Suthar and Huang, {Jung Y.} and Santhosh Chidangil",
year = "2017",
month = "1",
day = "1",
doi = "10.1117/12.2296863",
language = "English",
volume = "10438",
editor = "Buller, {Gerald S.} and Lewis, {Keith L.} and Hollins, {Richard C.} and Lamb, {Robert A.}",
booktitle = "Emerging Imaging and Sensing Technologies for Security and Defence II",
publisher = "SPIE",
address = "United States",

}

Suthar, G, Huang, JY & Chidangil, S 2017, Optimisation and evaluation of hyperspectral imaging system using machine learning algorithm. in GS Buller, KL Lewis, RC Hollins & RA Lamb (eds), Emerging Imaging and Sensing Technologies for Security and Defence II. vol. 10438, 104380L, SPIE, Emerging Imaging and Sensing Technologies for Security and Defence II 2017, Warsaw, Poland, 13-09-17. https://doi.org/10.1117/12.2296863

Optimisation and evaluation of hyperspectral imaging system using machine learning algorithm. / Suthar, Gajendra; Huang, Jung Y.; Chidangil, Santhosh.

Emerging Imaging and Sensing Technologies for Security and Defence II. ed. / Gerald S. Buller; Keith L. Lewis; Richard C. Hollins; Robert A. Lamb. Vol. 10438 SPIE, 2017. 104380L.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Optimisation and evaluation of hyperspectral imaging system using machine learning algorithm

AU - Suthar, Gajendra

AU - Huang, Jung Y.

AU - Chidangil, Santhosh

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Hyperspectral imaging (HSI), also called imaging spectrometer, originated from remote sensing. Hyperspectral imaging is an emerging imaging modality for medical applications, especially in disease diagnosis and image-guided surgery. HSI acquires a three-dimensional dataset called hypercube, with two spatial dimensions and one spectral dimension. Spatially resolved spectral imaging obtained by HSI provides diagnostic information about the objects physiology, morphology, and composition. The present work involves testing and evaluating the performance of the hyperspectral imaging system. The methodology involved manually taking reflectance of the object in many images or scan of the object. The object used for the evaluation of the system was cabbage and tomato. The data is further converted to the required format and the analysis is done using machine learning algorithm. The machine learning algorithms applied were able to distinguish between the object present in the hypercube obtain by the scan. It was concluded from the results that system was working as expected. This was observed by the different spectra obtained by using the machine-learning algorithm.

AB - Hyperspectral imaging (HSI), also called imaging spectrometer, originated from remote sensing. Hyperspectral imaging is an emerging imaging modality for medical applications, especially in disease diagnosis and image-guided surgery. HSI acquires a three-dimensional dataset called hypercube, with two spatial dimensions and one spectral dimension. Spatially resolved spectral imaging obtained by HSI provides diagnostic information about the objects physiology, morphology, and composition. The present work involves testing and evaluating the performance of the hyperspectral imaging system. The methodology involved manually taking reflectance of the object in many images or scan of the object. The object used for the evaluation of the system was cabbage and tomato. The data is further converted to the required format and the analysis is done using machine learning algorithm. The machine learning algorithms applied were able to distinguish between the object present in the hypercube obtain by the scan. It was concluded from the results that system was working as expected. This was observed by the different spectra obtained by using the machine-learning algorithm.

UR - http://www.scopus.com/inward/record.url?scp=85038447710&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85038447710&partnerID=8YFLogxK

U2 - 10.1117/12.2296863

DO - 10.1117/12.2296863

M3 - Conference contribution

AN - SCOPUS:85038447710

VL - 10438

BT - Emerging Imaging and Sensing Technologies for Security and Defence II

A2 - Buller, Gerald S.

A2 - Lewis, Keith L.

A2 - Hollins, Richard C.

A2 - Lamb, Robert A.

PB - SPIE

ER -

Suthar G, Huang JY, Chidangil S. Optimisation and evaluation of hyperspectral imaging system using machine learning algorithm. In Buller GS, Lewis KL, Hollins RC, Lamb RA, editors, Emerging Imaging and Sensing Technologies for Security and Defence II. Vol. 10438. SPIE. 2017. 104380L https://doi.org/10.1117/12.2296863