Abstract
Morphological attribute profiles are robust in capturing the spectral–spatial information of hyperspectral imagery. To incorporate maximum spatial information, generation of a profile using multiple attributes with large number of threshold values is a well-known approach. Although the profile contains very rich spatial information, at the same time its dimensionality increases. This raises two critical problems for hyperspectral image classification: (i) curse of dimensionality and (ii) computational complexity. To mitigate such problems, the only supervised feature selection technique that exists in the literature is computationally demanding. In this article, a fast supervised feature selection technique by exploiting rough set theory and genetic algorithms is proposed. Our technique computes the relevance and significance of each feature in the profile using rough set theory. Then, based on the relevance and significance values a novel fitness function of genetic algorithms is designed to select an optimal subset of features from the constructed profile. To show the effectiveness of the proposed technique, it is compared with the existing state-of-the-art technique by considering three real hyperspectral data sets.
Similar content being viewed by others
Notes
References
Abualigah LMQ, Hanandeh ES (2015) Applying genetic algorithms to information retrieval using vector space model. Int J Comput Sci Eng Appl 5(1):19–28
Abualigah LM, Khader AT (2017) Unsupervised text feature selection technique based on hybrid particle swarm optimization algorithm with genetic operators for the text clustering. J Supercomput 73(11):4773–4795
Barman B, Patra S (2019a) Empirical study of neighbourhood rough sets based band selection techniques for classification of hyperspectral images. IET Image Proc 13(8):1266–1279
Barman B, Patra S (2019b) A novel technique to detect a suboptimal threshold of neighborhood rough sets for hyperspectral band selection. Soft Comput 23:13709–13719
Benediktsson JA, Palmason JA, Sveinsson JR (2005) Classification of hyperspectral data from urban areas based on extended morphological profiles. IEEE Trans Geosci Remote Sens 43(3):480–491
Bhardwaj K, Patra S (2018) An unsupervised technique for optimal feature selection in attribute profiles for spectral–spatial classification of hyperspectral images. ISPRS J Photogramm Remote Sens 138:139–150
Bhardwaj K, Patra S, Bruzzone L (2019) Threshold-free attribute profile for classification of hyperspectral images. IEEE Trans Geosci Remote Sens 57(10):7731–7742
Blaschke T (2010) Object based image analysis for remote sensing. ISPRS J Photogramm Remote Sens 65(1):2–16
Cavallaro G, Falco N, Dalla Mura M, Benediktsson JA (2017) Automatic attribute profiles. IEEE Trans Image Process 26(4):1859–1872
Cekik R, Telceken S (2018) A new classification method based on rough sets theory. Soft Comput 22(6):1881–1889
Chang CI (2007) Hyperspectral data exploitation: theory and applications. Wiley, Hoboken
Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):27
Chen Y, Lin Z, Zhao X, Wang G, Gu Y (2014) Deep learning-based classification of hyperspectral data. IEEE J Sel Top Appl Earth Obs Remote Sens 7(6):2094–2107
Dalla Mura M, Atli Benediktsson J, Waske B, Bruzzone L (2010a) Extended profiles with morphological attribute filters for the analysis of hyperspectral data. Int J Remote Sens 31(22):5975–5991
Dalla Mura M, Benediktsson JA, Waske B, Bruzzone L (2010b) Morphological attribute profiles for the analysis of very high resolution images. IEEE Trans Geosci Remote Sens 48(10):3747–3762
Dalla Mura M, Villa A, Benediktsson JA, Chanussot J, Bruzzone L (2011) Classification of hyperspectral images by using extended morphological attribute profiles and independent component analysis. IEEE Geosci Remote Sens Lett 8(3):542–546
Falco N, Benediktsson JA, Bruzzone L (2015) Spectral and spatial classification of hyperspectral images based on ICA and reduced morphological attribute profiles. IEEE Trans Geosci Remote Sens 53(11):6223–6240
Fan Y, Zhang C, Liu Z, Qiu Z, He Y (2019) Cost-sensitive stacked sparse auto-encoder models to detect striped stem borer infestation on rice based on hyperspectral imaging. Knowl Based Syst 168:49–58
Fang L, Liu Z, Song W (2019) Deep hashing neural networks for hyperspectral image feature extraction. IEEE Geosci Remote Sens Lett 16(9):1412–1416
Fauvel M, Tarabalka Y, Benediktsson JA, Chanussot J, Tilton JC (2013) Advances in spectral–spatial classification of hyperspectral images. Proc IEEE 101(3):652–675
Feng L, Tan AH, Lim MH, Jiang SW (2016) Band selection for hyperspectral images using probabilistic memetic algorithm. Soft Comput 20(12):4685–4693
Ghamisi P, Benediktsson JA, Sveinsson JR (2014a) Automatic spectral–spatial classification framework based on attribute profiles and supervised feature extraction. IEEE Trans Geosci Remote Sens 52(9):5771–5782
Ghamisi P, Couceiro MS, Fauvel M, Benediktsson JA (2014b) Integration of segmentation techniques for classification of hyperspectral images. IEEE Geosci Remote Sens Lett 11(1):342–346
Ghamisi P, Dalla Mura M, Benediktsson JA (2015) A survey on spectral–spatial classification techniques based on attribute profiles. IEEE Trans Geosci Remote Sens 53(5):2335–2353
Ghamisi P, Plaza J, Chen Y, Li J, Plaza AJ (2017) Advanced spectral classifiers for hyperspectral images: a review. IEEE Geosci Remote Sens Mag 5(1):8–32
Goldberg DE (1989) Genetic algorithms in search, optimization and machine leaning. Addison Wesley, Reading
Hazir E, Erdinler ES, Koc KH (2018) Optimization of CNC cutting parameters using design of experiment (DOE) and desirability function. J For Res 29(5):1423–1434
Hughes G (1968) On the mean accuracy of statistical pattern recognizers. IEEE Trans Inf Theory 14(1):55–63
Kang X, Li S, Benediktsson JA (2014) Spectral–spatial hyperspectral image classification with edge-preserving filtering. IEEE Trans Geosci Remote Sens 52(5):2666–2677
Khan MJ, Khan HS, Yousaf A, Khurshid K, Abbas A (2018) Modern trends in hyperspectral image analysis: a review. IEEE Access 6:14118–14129
Kotsiantis S, Kanellopoulos D (2006) Discretization techniques: a recent survey. GESTS Int Trans Comput Sci Eng 32(1):47–58
Li W, Fu Z (2018) Unmanned aerial vehicle positioning based on multi-sensor information fusion. Geo Spatial Inf Sci 21(4):302–310
Liao W, Bellens R, Pizurica A, Philips W, Pi Y (2012) Classification of hyperspectral data over urban areas using directional morphological profiles and semi-supervised feature extraction. IEEE J Sel Top Appl Earth Obs Remote Sens 5(4):1177–1190
Mahmood Z, Thoonen G, Scheunders P (2012) Automatic threshold selection for morphological attribute profiles. In: 2012 IEEE International geoscience and remote sensing symposium (IGARSS), IEEE, pp 4946–4949
Maji P, Paul S (2010) Rough sets for selection of molecular descriptors to predict biological activity of molecules. IEEE Trans Syst Man Cybern Part C (Appl Rev) 40(6):639–648
Marpu PR, Pedergnana M, Mura MD, Peeters S, Benediktsson JA, Bruzzone L (2012) Classification of hyperspectral data using extended attribute profiles based on supervised and unsupervised feature extraction techniques. Int J Image Data Fusion 3(3):269–298
Marpu PR, Pedergnana M, Dalla Mura M, Benediktsson JA, Bruzzone L (2013) Automatic generation of standard deviation attribute profiles for spectral–spatial classification of remote sensing data. IEEE Geosci Remote Sens Lett 10(2):293–297
Patra S, Modi P, Bruzzone L (2015) Hyperspectral band selection based on rough set. IEEE Trans Geosci Remote Sens 53(10):5495–5503
Patra S, Bhardwaj K, Bruzzone L (2017) A spectral–spatial multicriteria active learning technique for hyperspectral image classification. IEEE J Sel Top Appl Earth Obs Remote Sens 10(12):5213–5227
Pawlak Z (1997) Rough set approach to knowledge-based decision support. Eur J Oper Res 99(1):48–57
Pedergnana M, Marpu PR, Dalla Mura M, Benediktsson JA, Bruzzone L (2013) A novel technique for optimal feature selection in attribute profiles based on genetic algorithms. IEEE Trans Geosci Remote Sens 51(6):3514–3528
Salembier P, Serra J (1995) Flat zones filtering, connected operators, and filters by reconstruction. IEEE Trans Image Process 4(8):1153–1160
Salembier P, Oliveras A, Garrido L (1998) Antiextensive connected operators for image and sequence processing. IEEE Trans Image Process 7(4):555–570
Shang R, Lan Y, Jiao L, Stolkin R (2018) A dynamic local cluster ratio-based band selection algorithm for hyperspectral images. Soft Comput 23(17):8281–8289
Soltani-Farani A, Rabiee HR (2015) When pixels team up: spatially weighted sparse coding for hyperspectral image classification. IEEE Geosci Remote Sens Lett 12(1):107–111
Tarabalka Y, Benediktsson JA, Chanussot J, Tilton JC (2010) Multiple spectral–spatial classification approach for hyperspectral data. IEEE Trans Geosci Remote Sens 48(11):4122–4132
Urbach ER, Roerdink JB, Wilkinson MH (2007) Connected shape-size pattern spectra for rotation and scale-invariant classification of gray-scale images. IEEE Trans Pattern Anal Mach Intell 29(2):272–285
Wang Q, Zhang F, Li X (2018) Optimal clustering framework for hyperspectral band selection. IEEE Trans Geosci Remote Sens 56(10):5910–5922
Yuan Y, Zheng X, Lu X (2017) Discovering diverse subset for unsupervised hyperspectral band selection. IEEE Trans Image Process 26(1):51–64
Zhu Z, Jia S, He S, Sun Y, Ji Z, Shen L (2015) Three-dimensional Gabor feature extraction for hyperspectral imagery classification using a memetic framework. Inf Sci 298:274–287
Acknowledgements
Authors would like to thank the Science and Engineering Research Board, Government of India, under which a project titled Development of Advanced Techniques for the Analysis of Remotely Sensed Images (Grant No. YSS/2014/000013) is being carried out at the Department of Computer Science and Engineering, Tezpur University, Assam.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interests regarding the publication of this paper.
Informed consent
Consent to submit has been received explicitly from all co-authors, as well as from the responsible authorities tacitly or explicitly at the institute/organization where the work has been carried out before the work is submitted.
Research involving human participants and/or animals
Our research does not include human participants or animals.
Additional information
Communicated by V. Loia.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Das, A., Patra, S. A rough-GA based optimal feature selection in attribute profiles for classification of hyperspectral imagery. Soft Comput 24, 12569–12585 (2020). https://doi.org/10.1007/s00500-020-04697-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-020-04697-y