An Original Method of Extraction Bands Based On Spectral And Spatial Characteristic To Reduce The Hyperspectral Image
How to Cite?
Agouzal Mehdi, Merzouqi Maria, Moha Arouch, "An Original Method of Extraction Bands Based On Spectral And Spatial Characteristic To Reduce The Hyperspectral Image," International Journal of Engineering Trends and Technology, vol. 70, no. 3, pp. 185-194, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I1P221
Reducing the dimensionality of HIS  is still a hot topic and a challenge to be won. Numerous studies have been devoted to this objective, using different strategies to find an efficient and rapid method. The effectiveness of an approach in this area refers to the ability to optimize the number of bands without loss of information and to improve classification performance. Well-known methods treat spatial and spectral image characteristics separately. However, the combined treatment of these characteristics turned out to be another aspect to be highlighted . In this article, a new reduction method is proposed, which is based on the fusion of the spatial-spectral characteristics. Specifically, it allowed the extraction of the spatial-spectral characteristic for all pixels. Then a measurement of the similarity of the spectral signatures is performed by the external spectral correlation to discern the unwanted bands. Then, discriminant analysis of the set selected from the first step is established by calculating the variance. After the descending ordering of the values of the variance of the spectral signatures of each pixel relative to the reference signature of each class, an adjustable selection percentage is used to count the repetition rate of the top brands in all classes to promote extraction performance while controlling the redundancy penalty. This method made it possible to reproduce a thematic map closer to the ground truth of Pavia. The experimental results obtained by SVM-RBF demonstrate the efficiency of the proposed method, whereby the total number of bands has been reduced from 103 to 35 with OA greater than 93%.
Reduction of dimensionality, Extraction method, Correlation, Variance, Spectral Signature, classification, RBF-SVM.
 T. Tr, Dimensionality Reduction: A Comparative Review, 36.
 Q. Man, P. Dong, and H. Guo, Pixel- and feature-level fusion of hyperspectral and lidar data for urban land-use classification, Int. J. Remote Sens., 36(6) (2015) 1618–1644.
 C.-I. Chang, Ed., Hyperspectral data exploitation: theory and applications. Hoboken, N.J: Wiley-Interscience, (2007).
 E. Adam, O. Mutanga, and D. Rugege, Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: a review, Wetl. Ecol. Manag., 18(3) (2010) 281–296.
 F. D. van der Meer et al., Multi- and hyperspectral geologic remote sensing: A review, Int. J. Appl. Earth Obs. Geoinformation, 14(1) (2012) 112–128.
 B. Fei, Hyperspectral imaging in medical applications, in Data Handling in Science and Technology, 32 (2020) 523–565.
 O. Mutanga, E. Adam, and M. A. Cho, High-density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm, Int. J. Appl. Earth Obs. Geoinformation, 18 (2012) 399–406.
 G. Hughes, On the mean accuracy of statistical pattern recognizers, IEEE Trans. Inf. Theory, 14(1) (1968) 55–63.
 M. Hasanlou and F. Samadzadegan, Comparative Study of Intrinsic Dimensionality Estimation and Dimension Reduction Techniques on Hyperspectral Images Using K-NN Classifier, IEEE Geosci. Remote Sens. Lett., 9(6) (2012) 1046–1050.
 J. Huang, Y. Cai, and X. Xu, A Filter Approach to Feature Selection Based on Mutual Information, in 2006 5th IEEE International Conference on Cognitive Informatics, Beijing, China, (2006) 84–89.
 Jinjie Huang, Yunze Cai, and Xiaoming Xu, A Wrapper for Feature Selection Based on Mutual Information, in 18th International Conference on Pattern Recognition (ICPR’06), Hong Kong, China, (2006) 618–621.
 M. Merzouqi, E. Sarhrouni, and A. Hammouch, Classification and Reduction of Hyperspectral Images Based on Motley Method, in Intelligent Systems Applications in Software Engineering, vol. 1046, R. Silhavy, P. Silhavy, and Z. Prokopova, Eds. Cham: pringer International Publishing, (2019) 155–164.
 M. Merzouqi, H. Nhaila, E. Sarhrouni, and A. Hammouch, Improved filter algorithm using inequality fano to select bands for HSI classification, in 2015 Intelligent Systems and Computer Vision (ISCV), Fez, Morocco, (2015) 1–5.
 R. Archibald and G. Fann, Feature Selection and Classification of Hyperspectral Images With Support Vector Machines, IEEE Geosci. Remote Sens. Lett., 4(4) (2007) 674–677.
 M. Agouzal and M. Arouch, A new method for hyperspectral reduction based on the trend of the electromagnetic range, in 2020 Fourth World Conference on Smart Trends in Systems, Security and Sustainability (WorldS4), London, United Kingdom, (2020) 782–787.
 X. Kang, S. Li, and J. A. Benediktsson, Feature Extraction of Hyperspectral Images With Image Fusion and Recursive Filtering, IEEE Trans. Geosci. Remote Sens., 52(6) 3742–3752 (2014).
 X. Ceamanos and S. Valero, Processing Hyperspectral Images, in Optical Remote Sensing of Land Surface, Elsevier, (2016) 163– 200.
 P. Mishra, M. S. M. Asaari, A. Herrero-Langreo, S. Lohumi, B. Diezma, and P. Scheunders, Close range hyperspectral imaging of plants: A review, Biosyst. Eng., 164 (2017) 49–67.
 J. M. Bioucas-Dias, A. Plaza, G. Camps-Valls, P. Scheunders, N. Nasrabadi, and J. Chanussot, Hyperspectral Remote Sensing Data Analysis and Future Challenges, IEEE Geosci. Remote Sens. Mag., 1(2) (2013) 6–36.
 C. Lee and D. A. Landgrebe, Feature extraction based on decision boundaries, IEEE Trans. Pattern Anal. Mach. Intell.,15(4) (1993) 388–400.
 T. H. Dat and C. Guan, Feature Selection Based on Fisher Ratio and Mutual Information Analyses for Robust Brain-Computer Interface, in 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP ’07, Honolulu, HI, USA, (2007) I-337-I–340.
 M. Fauvel, Y. Tarabalka, J. A. Benediktsson, J. Chanussot, and J.C.Tilton, Advances in Spectral-Spatial Classification of Hyperspectral Images, Proc. IEEE, 101(3) (2013) 652-675.
 C. F. Lam and D. Kamins, Signature recognition through spectral analysis, Pattern Recognit., 22(1) 39–44 (1989).
 C. Xu, I. Kim, and S. G. Kong, Feature level fusion for hyperspectral images, Orlando, Florida, USA, May (2009) 73150N.
 B. Bigdeli, F. Samadzadegan, and P. Reinartz, A decision fusion method based on multiple support vector machine system for fusion of hyperspectral and LIDAR data, Int. J. Image Data Fusion, 5(3) (2014) 196–209.
 O. Sharifi, M. Mokhtarzadeh, and B. Asghari Beirami, A new deep learning approach for classification of hyperspectral images: feature and decision level fusion of spectral and spatial features in multiscale CNN, Geocarto Int., (2021) 1–26.
 M. M. Khattab, A. M. Zeki, A. A. Alwan, and A. S. Badawy, Regularization-based multi-frame super-resolution: A systematic review, J. King Saud Univ. - Comput. Inf. Sci., 32(7) (2020) 755– 762.
 V. De Witte, G. Thoonen, P. Scheunders, A. Pizurica, and W. Philips, Classification of multi-source images using color morphological profiles, in 2011 IEEE International Geoscience and Remote Sensing Symposium, Vancouver, BC, Canada, (2011) 3919–3922.
 Y. Nanyam, R. Choudhary, L. Gupta, and J. Paliwal, A decisionfusion strategy for fruit quality inspection using hyperspectral imaging, Biosyst. Eng., 111(1) (2012) 118–125.
 A. Tamim, Segmentation et classification des images satellitaires: application à la détection des zones d’upwelling côtier marocain et mise en place d’un logiciel de suivi spatiotemporel, 93.
 K. Wang, X. Gu, T. Yu, Q. Meng, L. Zhao, and L. Feng, Classification of hyperspectral remote sensing images using frequency spectrum similarity, Sci. China Technol. Sci.,56(4) (2013) 980–988.
 J. Yue, W. Zhao, S. Mao, and H. Liu, Spectral–spatial classification of hyperspectral images using deep convolutional neural networks, Remote Sens. Lett., 6(6) (2015) 468–477.
 Y. Tarabalka, J. A. Benediktsson, J. Chanussot, and J. C. Tilton, Multiple Spectral–Spatial Classification Approach for Hyperspectral Data, IEEE Trans. Geosci. Remote Sens., (2010) 5570985.
 H. Akoglu, User’s guide to correlation coefficients, Turk. J. Emerg. Med., 18(3) (2018) 91–93.
 S. J. Reeves and Zhao Zhe, Sequential algorithms for observation selection, IEEE Trans. Signal Process., 47(1) (1999) 123–132.
 J. Zhao et al., FeatureExplorer: Interactive Feature Selection and Exploration of Regression Models for Hyperspectral Images, in 2019 IEEE Visualization Conference (VIS), Vancouver, BC, Canada, (2019) 161–165.
 P. Lasch and I. Noda, Two-Dimensional Correlation Spectroscopy for Multimodal Analysis of FT-IR, Raman, and MALDI-TOF MS Hyperspectral Images with Hamster Brain Tissue, Anal. Chem., 89(9) (2017) 5008–5016.
 S. Bourennane, C. Fossati, and A. Cailly, Improvement of Classification for Hyperspectral Images Based on Tensor Modeling, IEEE Geosci. Remote Sens. Lett.,7(4) (2010) 801–805.
 M. R. Gupta and N. P. Jacobson, Wavelet Principal Component Analysis and its Application to Hyperspectral Images, in 2006 International Conference on Image Processing, Atlanta, GA,(2006) 1585–1588.
 F. Mirzapour and H. Ghassemian, Improving hyperspectral image classification by combining spectral, texture, and shape features, Int. J. Remote Sens., 36(4) (2015) 1070–1096.
 S. Singh, D. Srivastava, and S. Agarwal, GLCM and its application in pattern recognition, in 2017 5th International Symposium on Computational and Business Intelligence (ISCBI), Dubai, United Arab Emirates, (2017) 20–25.
 R. Eyraud, Classification, Apprentissage, Décision, 30.
 B.-C. Kuo, H.-H. Ho, C.-H. Li, C.-C. Hung, and J.-S. Taur, A Kernel-Based Feature Selection Method for SVM With RBF Kernel for Hyperspectral Image Classification, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.,7(1) (2014) 317–326.
 S. Zhang, X. Li, M. Zong, X. Zhu, and D. Cheng, Learning k for kNN Classification, ACM Trans. Intell. Syst. Technol., 8(3) (2017) 1–19.
 M. Maria, S. El Kebir, and H. Ahmed, Reduction dimensionality of hyperspectral imagery using genetic algorithm and mutual information and normalized mutual information as a fitness function, Int. Rev. Appl. Sci. Eng., 12(1) (2021) 64–75.
 M. Maria, Reduction of the Hyperspectral images Dimensionality Using a New Genetic Algorithm Procedure, 15(3) (2020) 12.
 R. Doerffer, B. Kunkel, and H. van der Piepen, Rosis - An Imaging Spectrometer For Rejiote Sensing Of Chlorophyll Fluorescence, Los Angeles, CA, United States, (1989) 36.
 M, Merzouqi, M, Agouzal, E, Sarhrouni, A, Hammouch. A study of a proposed suboptimal selection strategy based on genetic algorithm and filters of mutual information. International Journal of Engineering Trends and Technology (IJETT), 69(11) (2021).