Abstract
The main objective of hyperspectral Image Classification is to group pixels into spectral classes, where each class having a unique label representing specific information in the image. The classification can be done using methods categorized as supervised and unsupervised. The contrast of hyperspectral images is degraded if there is any disturbance of the transmission medium. This disturbance degrades the quality of the image generated by the sensor, which effects the classification accuracy. In this paper, Genetic Algorithm (GA) is used for hyperspectral image analysis. The algorithm is used in contrast enhancement, dimensionality reduction, and classification. This dimensionality reduction will remove less informative bands, decrease storage space, computational load, and communication bandwidth. The experimental results show the improvement of accuracy in classifying Indian Pines and Pavia University datasets
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Harikiran, J. et.al.: Fast clustering algorithms for segmentation of microarray images. IJSER 5(10), 569–574 (2014)
Saichandana, B. et al.: Image fusion in hyperspectral image classification using genetic algorithm. IJEECS 2(3), 703–711 (2016)
Saichandana, B., et al.: Dimensionality reduction and classification of hyperspectral images using genetic algorithm. IJEECS 3(3), 503–511 (2016)
Holland, J.: Adaptation in natural and artificial systems. Univ. of Michigan Press, Ann Arbor, MI (1975)
Zeiler, A. et al.: Empirical mode decomposition—an introduction. In: Proceedings of IEEE IJCNN, pp. 1–8 (2010)
Yin, J., et al.: A new dimensionality reduction algorithm for hyperspectral image using evolutionary strategy. IEEE Trans. Industr. Inform. 8(4), 935–943 (2012)
Deb, K. et al.: A computationally efficient evolutionary algorithm for real parameter optimization. IEEE Trans. Evol. Comp. 10(4), 371–395 (1998)
Du, Q. et al.: Similarity based unsupervised band selection for hyperspectral image analysis. IEEE Tran. Geos. RS Lett. 5(4), 564–568 (2008)
Gharaati, E. et al.: A new band selection method for hyperspectral images based on constrained optimization. In: Proceedings of IEEE ICIKT, pp. 1–6 (2015)
Hongjun, Su., Qian, Du., Peijun, Du.: Hyperspectral image visualization using band selection. IEEE JSTAEORS 10(4), 2647–2658 (2013)
Tarabalka, Y., et al.: Spectral-spatial classification of hyperspectral imagery based on partitional clustering techniques. IEEE Trans. Geos. Remote Sens. 47(5), 2973–2987 (2009)
Zhang, H., et al.: Hyperspectral image restoration using low-rank matrix recovery. IEEE Trans. Geo. RS 52(8), 4729–4743 (2014)
Ngatchou, P. et al.: Pareto multi objective optimization. In: Proceedings of 13th ICISAPS. IEEE (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Subba Reddy, T., Harikiran, J., Sai Chandana, B. (2021). Multi-Objective Genetic Algorithm for Hyperspectral Image Analysis. In: Satapathy, S.C., Bhateja, V., Favorskaya, M.N., Adilakshmi, T. (eds) Smart Computing Techniques and Applications. Smart Innovation, Systems and Technologies, vol 225. Springer, Singapore. https://doi.org/10.1007/978-981-16-0878-0_61
Download citation
DOI: https://doi.org/10.1007/978-981-16-0878-0_61
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-0877-3
Online ISBN: 978-981-16-0878-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)