Hyperspectral Image Segmentation Using Evolutionary Multifactorial Spectral Analysis for OMEGA Dataset

  • Nagarajan Munusamy
  • Rashmi P. Karchi
Conference paper


Mars region is being imaged with an exceptional combination of spectral and spatial resolution spectrometer using OMEGA instrument. The hyperspectral images of Mars provide spectral range and chemical species with high resolution. This paper presents a novel unsupervised segmentation algorithm named as evolutionary component analysis for remotely sensed hyperspectral image data for material identification in the spatial and spectral information. Sparse multinomial logistic regression (SMLR) algorithm is initially employed to learn the posterior probability distributions from the spatial and spectral information of the images containing class imbalance information to infer the class distribution of the testing hyperspectral data. Evolutionary multifactorial spectral analysis (ESA) helps to characterize noise and extremely mixed pixels with less training set with high training quality and utility with respect to spectral signatures and its spectral changes with less interaction for classification and end-member detection. The proposed segmentation approach based on ESA is investigated and estimated using both real and simulated hyperspectral datasets. ESA is evaluated for the endmember extraction in the mixed pixel revealing up-to-date performance when compared with advanced hyperspectral image classification techniques. The combined spatial–contextual information (ESA + SMLR) characterizes a state-of-the-art contribution in the research field of material identification. The proposed approach is exposed to present proper classification of the minerals of Mars surface in both the spatial and the spectral domain in short span of time.


Evolutionary multifactorial spectral analysis Hyperspectral image classification Mineral identification Spectral analysis 



Sparse multinomial logistic regression


Evolutionary multifactorial spectral analysis


Observatoire pour la Minéralogie, l’Eau, les Glaces et l’Activité


Environment for Visualizing Images


  1. 1.
    Clark RN, Swayze GA, Wise R, Livo KE, Kokaly RF, Sutley SJ, Dalton JB, McDougal RR, Gent CA (2003) Imaging spectroscopy: earth and planetary remote sensing with the USGS Tetracorder and expert systems. J Geophys Res 108(E12):5–1CrossRefGoogle Scholar
  2. 2.
    Dalton JB, Sutter B, Kramer MG, Stockstill KR, Moersch J, Moore J (2003) Searching for aqueous mineralogy on Mars utilizing a surface water flow model Mars global surveyor and Mars odyssey data. American Geophysical Union, Fall Meeting, Abstract #P21B-0052Google Scholar
  3. 3.
    Ezhilarasi, M., Krishnaveni V. “An evolutionary multipath energy-efficient routing protocol (EMEER) for network lifetime enhancement in wireless sensor networks” Soft Computing, (2019). Scholar
  4. 4.
    Forni O, Poulet F, Bibring JP, Erard S Gomez C, Langevin Y, Gondet B (2005) The Omega Science Team, 2005. Component separation of OMEGA spectra with ICA. In: 36th annual lunar and planetary science conference, March, abstract no.1623,Google Scholar
  5. 5.
    Angadi SA, Hatture SM (2011) A novel spectral graph theoretic approach to user identification using hand geometry. Int J Mac Intell 3(4):282–288Google Scholar
  6. 6.
    Karchi RP, Munusamy N (2018) Hyperspectral image classification and Unmixing by using ART and SUnSPI techniques. Int J Database Theory Appl 11(3):13–28Google Scholar
  7. 7.
    Moussaoui S, Hauksdóttir H, Schmidt F, Jutten C, Chanussot J, Brie D, Douté S, Benediktsson JA (2008) On the decomposition of Mars hyperspectral data by ICA and Bayesian positive source separation. Neurocomputing 71:2194CrossRefGoogle Scholar
  8. 8.
    Shuyuan Y, Qiao Y, Yang L, Jin P, Jiao L (2014) Hyperspectral image classification based on relaxed clustering assumption and spatial Laplace Regularizer. IEEE Geosci Remote Sens LettGoogle Scholar
  9. 9.
    Combe J-P, Le Mouélic S, Sotin C, Gendrin A (2008) Analysis of OMEGA/MarsExpress data hyperspectral data using a multiple-endmember linear spectral Unmixing model (MELSUM): methodology and first results. Planet Space Sci 56:951CrossRefGoogle Scholar
  10. 10.
    Karchi RP, Munusamy N (2018) Exploration of Unmixing and classification of hyperspectral imagery. Int J Futur Gener Commun Netw (IJFGCN) 11(6):13–31Google Scholar
  11. 11.
  12. 12.
    Bibring J-P, Soufflot A, Berthe M, Angevin Y, Gondet B, Drossart P, Bouye M, Combes M, Puget P, Semery A, Bellucci G, Formisano V, Moroz V, Kottsov V (2004) The OMEGA Co-I team, 2004. Eur Space Agency Spec Pb 1240:37Google Scholar
  13. 13.
    Bibring J-P, Langevin Y, Gendrin A, Gondet B, Poulet F, Berthe M, Soufflot A, Arvidson R, Mangold N, Mustard JF, Drossart P (2005) The OMEGA team, 2005. Mars surface diversity as revealed by the OMEGA/Mars express observations. Science 307(5715):1576–1581CrossRefGoogle Scholar
  14. 14.
    Gu YF, Feng K (2012) L1-graph Semisupervised learning for hyperspectral image classification. In: IEEE proceedings of international geosciences remote sensing symposium, Munich, Germany, pp 1401–1404,Google Scholar
  15. 15.
    Gupta A, Ong YS, Feng L (2015) Multifactorial evolution: towards evolutionary multitasking. IEEE Trans Evol Comput 20(3):343–357CrossRefGoogle Scholar
  16. 16.
    Nagarajan M, Karthikeyan S (2012) A new approach to increase the life time and efficiency of wireless sensor network. In: Proceedings of IEEE international conference on pattern recognition, informatics and medical engineeringGoogle Scholar
  17. 17.
    Ezhilarasi M, Krishnaveni V (2018) A survey on wireless sensor network: energy and lifetime perspective. Taga J 14:3099–3113Google Scholar
  18. 18.
    Angadi SA, Hatture SM (2019) Face recognition through symbolic modelling of face graphs and texture. Int J Pattern Recognit Artif Intell. Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of Computer StudiesKSG College of Arts and ScienceCoimbatoreIndia
  2. 2.Bharathiar UniversityCoimbatoreIndia

Personalised recommendations