Abstract Hyperspectral Images (HSIs) represent an important source of information in the remote sensing field. Indeed, HSIs, which collect data in many spectral bands, are more simple interpretable and provide a detailed information about interest areas. However, hyperspectral imaging systems generate a huge amount of redundant data and an important level of noise. Dimensionality reduction is an important task that attempts to reduce dimensionality and remove noise so as to enhance the accuracy of remote sensing applications. The first dimensionality reduction approaches date back to 1970s, and various model-based methods have been proposed since these years. This field has known an increasing attention by the suggestion of graph based models that have yielded promising results. While graph based approaches generate considerable outputs, these models require often an important processing time to handle data. In this work, we aim to reduce the computational burden of a promising graph based method called the Modified Schroedinger Eigenmap Projections (MSEP). In this respect, we suggest an efficient superpixel algorithm, called Improved Simple Linear Iterative Clustering (Improved SLIC), to lessen the heavy computational load of the MSEP method. The proposed approach exploits the superpixels as inputs instead of pixels; and then runs the MSEP algorithm. While respecting the HSIs properties, the proposed scheme illustrates that the MSEP method can be performed with computational efficiency.

References

[1] Achanta R., Shaji A., Smith K., Lucchi A., Fua P., and Susstrunk S., “SLIC Superpixels Compared to State-of-the-Art Superpixel Methods,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 11, pp. 2274-2282, 2012.

[2] Chang C. and Lin C., “LIBSVM: A Library for Support Vector Machines,” ACM Transactions on Intelligent Systems and Technology, vol. 2, no. 3, pp. 1-27, 2011.

[3] Choong M., Khong W., Chin R., Wong F., and Teo K., “Clustering Algorithm in Normalised Cuts Based Image Segmentation,” in Proccedings of the 7th Asia Modelling Symposium, Hong Kong, pp. 166-171, 2013.

[4] Choong M., Kow W., Chin Y., Angeline L., and Teo K., “Image Segmentation Via Normalised Cuts and Clustering Algorithm,” in Proccedings of the IEEE International Conference on Control System, Computing and Engineering, Penang, pp. 430-435, 2012.

[5] Computational Intelligence Search Group Site, Hyperspectral Remote Sensing Scenes, http://www.ehu.eus/ccwintco/index.php?title=Hy perspectral_Remote_Sensing_Scenes, Last Visited, 2020.

[6] Fejjari A., Ettabaa K., and Korbaa O., “Spatial Spectral Schroedinger Eigenmaps Approach Based on Spectral Angle Distance for Hyperspectral Imagery Classification,” Journal of the Indian Society of Remote Sensing, vol. 49, pp. 689-2700, 2021.

[7] Fejjari A., Ettabaa K., and Korbaa O., “Intrinsic Decomposition based Tensor Modeling Scheme for Hyperspectral Target Detection,” in Proccedings of IEEE International Conference on Systems, Man, and Cybernetics, Toronto, pp. 2541-2546, 2020.

[8] Fejjari A., Ettabaa K., and Korbaa O., “Feature Extraction Techniques for Hyperspectral Images Classification,” in Proceedings of the 8th International Workshop Soft Computing Applications, Arad, pp. 174-188, 2018.

[9] Fejjari A., Saheb Ettabaa K., and Korbaa O., “Modified Schroedinger Eigenmap Projections Algorithm for Hyperspectral Imagery Classification,” in Proceedings of IEEE/ACS 14th International Conference on Computer Systems and Applications, Hammamet, pp. 809-814, 2017.

[10] Guimarães S., Kenmochi Y., Cousty J., Patrocinio Z., and Najman L., “Hierarchizing Graph-Based Image Segmentation Algorithms Relying on Region Dissimilarity: The Case of The Felzenszwalb-Huttenlocher Method,” Mathematical Morphology-Theory and Applications, vol. 2, no. 1, 2017.

[11] Johnson J., Schroedinger Eigenmaps for Manifold Alignment of Multimodal Hyperspectral Images, Thesis Rochester Institute of Technology, 2016. Improved Superpixels Generation Algorithm for Qualified... 955

[12] Kang X., Li S., Fang L., and Benediktsson J., “Intrinsic Image Decomposition for Feature Extraction of Hyperspectral Images,” IEEE Transactions on Geoscience and Remote Sensing, vol. 53, no. 4, pp. 2241-2253, 2015.

[13] Kim K., Zhang D., Kang M., and Ko S., “Improved Simple Linear Iterative Clustering Superpixels,” in Proceedings of IEEE 17th International Symposium on Consumer Electronics, Hsinchu, pp. 259-260, 2013.

[14] Kurz T. and Buckley S., “A Review of Hyperspectral Imaging in Close Range Applications,” in Proccedings of the XXIII International Society for Photogrammetry and Remote Sensing Congress, Prague, pp. 865-870, 2016.

[15] Luo H., Tang Y., Li C., and Yang L., “Local and Global Geometric Structure Preserving and Application to Hyperspectral Image Classification,” Mathematical Problems in Engineering, 2015.

[16] Moore A., Prince S., and Warrell J., “Lattice Cut- Constructing Superpixels Using Layer Constraints,” in Proccedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, pp. 2117-2124, 2010.

[17] Moore A., Prince S., Warrell J., Mohammed U., and Jones G., “Superpixel Lattices,” in Proccedings of IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, pp. 1-8, 2008.

[18] Veligandan S. and Rengasari N., “Hyperspectral Image Segmentation Based on Enhanced Estimation of Centroid with Fast KMeans,” The International Arab Journal of Information Technology, vol. 15, no. 5, pp. 904-911, 2018.

[19] Wang L. and Zhao D., Hyperspectral Image Processing, National Defense Industry Press, 2016.

[20] Xu J., Esquerre C., and Sun D., “Methods for Performing Dimensionality Reduction in Hyperspectral Image Classification,” Journal of Near Infrared Spectroscopy, vol. 26, no.1, pp. 61-75, 2018.

[21] Zhai Y., Zhang L., Wang N., Guo Y., Cen Y., Wu T., and Tong Q., “A Modified Locality- Preserving Projection Approach for Hyperspectral Image Classification,” IEEE Geoscience and Remote Sensing Letters, vol. 13, no. 8, pp. 1059-1063, 2016.

[22] Zhang L., Su H., and Shen J., “Hyperspectral Dimensionality Reduction Based on Multiscale Superpixelwise Kernel Principal Component Analysis,” Remote Sensing, vol. 11, no. 10, 2019.

[23] Zhang X., Chew S., Xu Z., and Cahill N., “SLIC Superpixels for Efficient Graph-Based Dimensionality Reduction of Hyperspectral Imagery,” SPIE Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXI 947209, 2015. Asma Fejjari holds a PhD in Computer Science from the University of Sousse (Tunisia) since 2020. She is carrying out her PostDoctoral research activities in the Faculty of Information and Communication Technology of the University of Malta. Her main research field includes Machine Learning, Image Processing and Computer Vision Karim Saheb Ettabaa received his PhD Degree in Signal Processing from Télécom Bretagne (France) in 2007. In 2016, he obtained the Habilitation to Supervise Researches degree in Signal Processing from the University of Rennes I (France). He is currently an Assistant Teacher at the University of Sousse. His research field includes Image-Signal Processing, Machine Learnig and Spatial Analysis. Ouajdi Korbaa obtained in 1995 the Engineering degree from the Ecole Centrale of Lille (France). He is Ph.D. in Production Management, Automatic Control and Computer Sciences of the University of Sciences and Technologies of Lille (France) since 1998. He also obtained, from the same university, the Habilitation to Supervise Researches degree in Computer Sciences in 2003. He is full Professor in the University of Sousse. He published around 150 research papers on scheduling, performance evaluation, discrete optimization.