Modified Graph-Based Algorithm for Efficient Hyperspectral Feature Extraction
Since the Laplacian Eigenmaps (LE) algorithm suffers from a spectral uncertainty problem for the adjacency weighted matrix construction, it may not be adequate for the hyperspectral dimension reduction (DR), classification or detection process. Moreover, only local neighboring data point’s properties are conserved in the LE method. To resolve these limitations, an improved feature extraction technique called modified Laplacian Eigenmaps (MLE) for hyperspectral images is suggested in this paper. The proposed approach determines the similarity between pixel and endmember for the purpose of building a more precise weighted matrix. Then, based on the obtained weighted matrix, the DR data are derived as the Laplacian eigenvectors of the Laplacian matrix, constructed from the weighted matrix. Furthermore, the novel proposed approach focuses on maximizing the distance between no nearby neighboring points, which raises the separability among ground objects. Compared to the original LE method, experiment results, for hyperspectral images classification and detection tasks, have proved an enhanced accuracy.
KeywordsLaplacian eigenmaps Hyperspectral dimension reduction Endmember extraction Hyperspectral images
This work was supported and financed by the Ministry of Higher Education and Scientific Research of Tunisia.
- 2.Khodr, J., Younes, R.: Dimensionality reduction on hyperspectral images: a comparative review based on artificial datas. In: 2011 4th International Congress on Image and Signal Processing, pp. 1875–1883. IEEE, Shanghai, China (2011)Google Scholar
- 4.Computational Intelligence search group site. http://www.ehu.eus/ccwintco/index.php?title = Hyperspectral_Remote_Sensing_Scenes. Last accessed 05 Dec 2017
- 6.Xudong Kang’s home page. http://xudongkang.weebly.com/data-sets.html. Last accessed 24 Dec 2017
- 7.Alvey, B., Zare, A., Cook, M., Ho, D.K.C.: Adaptive coherence estimator (ACE) for explosive hazard detection using wideband electromagnetic induction (WEMI). In: SPIE Conference Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXI, Baltimore (2016)Google Scholar
- 9.Fejjari, A., Saheb Ettabaa, K., Korbaa, O.: Modified schroedinger eigenmap projections algorithm for hyperspectral imagery classification. In: IEEE/ACS 14th International Conference on Computer Systems and Applications (AICCSA), pp. 809–814. IEEE, Hamammet, Tunisia (2017)Google Scholar