Abstract In this paper, the segmentation process is observant on hyperspectral satellite images. A novel approach, hyperspectral image segmentation based on enhanced estimation of centroid with unsupervised clusters such as fast k-means, fast k-means (weight), and fast k-means (careful seeding) has been addressed. Besides, a cohesive image segmentation approach based on inter-band clustering and intra-band clustering is processed. Moreover, the inter band clustering is accomplished by above clustering algorithms, while the intra band clustering is effectuated using Particle Swarm Clustering algorithm (PSC) with Enhanced Estimation of Centroid (EEOC). The hyperspectral bands are clustered and a single band which has a paramount variance from each cluster is opting for. This constructs the diminished set of bands. Finally, PSC EEOC carried out the segmentation process on the diminished bands. In addition, we compare the result produce in these methods by statistical analysis based on number of pixel, fitness value, and elapsed time.

References

[1] Arthur D. and Vassilvitskii S., K-means++: The Advantages of Careful Seeding, in Proceedings of the 8th Annual ACM-SIAM Symposium on Discrete Algorithms, New Orleans, pp. 1027- 1035, 2007.

[2] Celik T., Unsupervised Change Detection in Satellite Images Using Principle Component Analysis and K-Means Clustering, IEEE Geoscience and Remote Sensing Letters, vol. 6, no. 4, pp. 772-776, 2009.

[3] Khodadazadeh M., Li J., Plaza A., Ghassemian H., Bioucas-Dias J., and Li X., Spectral-Spatial Classification of Hyperspectral Data using Local and Global Probabilities for Mixed Pixel Hyperspectral Image Segmentation Based on Enhanced Estimation of ... 911 Characterization, IEEE Geoscience and Remote Sensing, vol. 52, no. 10, pp. 6298-6314, 2014.

[4] Li J., Bioucas-Dias J., and Plaza A., Spectral- Spatial Hyperspectral Image Segmentation Using Subspace Multinomial Logistic Regression and Markov Random Field, IEEE Geosciences and Remote Sensing, vol. 50, no. 3, pp. 809-823, 2012.

[5] Li J., Bioucas-Dias J., and Plaza A., Hyperspectral Image Segmentation Using A New Bayesian Approach with Active Learning, IEEE Geoscience and Remote Sensing, vol. 49, no. 10, pp. 3947-3960, 2011.

[6] Mohsen F., Hadhoud M., Mostafa K., and Amin K., A New Image Segmentation Method Based on Particle Swarm Optimization, The International Arab Journal of Information Technology, vol. 9, no. 5, pp. 487-493, 2012.

[7] Plaza A., Benediktsson J., Boardman J., Brazile J., Bruzzone L., Camps-Valls G., Chanussot J., Fauve M., GambaP., Gualtieri A., Marconcini M., Tilton J., and Trianni G., Recent Advances in Techniques for Hyperspectral Image Processing, Remote Sensing of Environment, vol. 113, supplement. 1, pp. s110-s122, 2009.

[8] Plaza A., Valencia D., Plaza J., and Martinez P., Commodity Cluster-Based Parallel Processing of Hyperspectral Imagery, Journal of Parallel and Distributed Computing, vol. 66, no. 3, pp. 345-358, 2006.

[9] Song B., Li J., Mura M., Li P., Plaza A., Bioucas- Dias J., Benediktsson J., and Chanussot J., Remotely Sensed Image Classification using Sparse Representations of Morphological Attribute Profiles, IEEE Geoscience and Remote Sensing, vol. 52, no. 8, pp. 5122-5136, 2014.

[10] Tarabalka Y., Benediktsson J., and Chanussot J., Spectral-Spatial Classification of Hyperspectral Imagery Based On Partitional Clustering Techniques, IEEE Geoscience and Remote Sensing, vol. 47, no. 8, pp. 2973-2987, 2009.

[11] Theiler J. and Gisler G., Contiguity-Enhanced K-Means Clustering Algorithm for Unsupervised Multispectral Image Segmentation, in Proceedings SPIE 3156, Algorithms, Devices and System for Optical Information Processing, San Diego, pp. 108-118, 1997.

[12] Veligandan S., Prakasam S., Rengasari N., and Kavitha M., Multiband Image Segmentation by using Enhanced Estimation of Centroid (EEOC), Information Journal-Japan, vol. 17, no. 6, pp. 1967-1980, 2014.

[13] Veligandan S. and Rengasari N., A Survey of Hyperspectral Image Segmentation Techniques for Multiband Reduction, Australian Journal of Basic and Applied Sciences, vol. 9, no. 7, pp. 446-451, 2015.

[14] Veligandan S. and Rengasari N., Hyperspectral Image Segmentation Based on Particle Swarm Optimization with Classical Clustering Methods, Advances in Natural and Applied Sciences, vol. 9, no. 12, pp. 45- 53, 2015.

[15] Veligandan S. and Rengasari N., Segmentation of Hyperspectral Image using JSEG based on Unsupervised Clustering Algorithms, ICTACT Journal on Image and Video Processing, vol. 6, no. 2, pp. 1152-1158, 2015.

[16] Yassine I. and Belfkih S., Texture Image Segmentation Using A New Descriptor and Mathematical Morphology, The International Arab Journal of Information Technology, vol. 10, no. 2, pp. 204-208, 2013. Saravana Kumar Veligandan is a research scholar in Manonmaniam Sundaranar University, Tirunelveli, Tamilnadu, India. He received his M.Sc.,

[Statistics] and M.Tech

[Computer and Information Technology] from same University. He was a faculty in the department of Computer Science and Engineering, as Asst. Prof in SCAD College of Engineering & Tech and Jayamatha Engineering College. At present he is working as Faculty in Centre for Bioinformatics, Pondicherry University. His area of interest is Image Processing, Pattern Recognition and Data mining. Naganathan Rengasari is a Professor in the Department of Computer Science and Engineering, Hindustan University, Chennai, India since June 2012. He was a faculty at various levels in the Department of Computer Science and Engineering, Alagappa University, Karaikudi, Tamilnadu, India during 1986-2008 and other Institutions between 2008- 2012. He has received M.Sc.

[Applied Mathematics] from Madurai Kamaraj University, India; M.Tech.

[Computer and Information Technology] from Manonmaniam Sundaranar University, India and Ph.D. in Computer Applications from Alagappa University. His area of interests is Network Security, Information Security, Algorithm, and Data Mining. He has 78 research publications to his credit in International/ National Journals/Conferences. He is a member of ACM, IET, CSI, ISTE, and ACCS.