Hyperspectral_OptimalSpectralClustering

Compute the optimal number of bands essential for dimensionaity reduction

Description and References

• The work done in this research is published as Part of the Communications in Computer and Information Science(CCIS), Springer, Book Series Volume 1035
• Title of the paper - Optimal Selection of Bands for Hyperspectral Images using Spectral Clustering - Vanshika Gupta (1), Sharad Kumar Gupta (2), Dericks P. Shukla (3)
• Link - https://link.springer.com/chapter/10.1007/978-981-13-9181-1_26 or Researchgate
• The work was carried out at IIT Mandi, under the guidance of Mr. Sharad Kumar Gupta @Sharadgupta27 and Dr. Dericks P. Shukla, during the IASc-INSA-NASI Summer Research Fellowship (Indian Academy of Sciences- Indian National Science Academy- National Academy of Science India) funded internship program.
• The repository is currently maintained by @vansjyo
• In case of queries, feel free to contact me through my email ID vanshika421@gmail.com
• For contributions or opening issues, please make a pull reuqest or open issues respectively.

Steps to run the program

• Clone/Download_Zip the repository
• Open MATLAB and connect to the folder Similarity_Matrices
• Modify the code for your input hyperspectral image
• Run any of the codes in the folder for computing the similarity/Adjacency matrix.
• Now connect to the folder Main
• Modify the inputs accordingly and run Sparse_SpectralClustering.m or Spectral_Clustering.m