Một số cải tiến kĩ thuật phân cụm cho ảnh viễn thám
Abstract
Clustering remote sensing images is an emerged topic that interests many researchers. Remote sensing images can have multi bands and high spatial resolution. Among a number of clustering algorithms such as KMeans, C-Means, Watersed, KMeans has been shown to be very performant. However, when applying on large size remote sensing images, converging speed of KMeans algorithm is still slow. Moreover, this algorithm considers only intensity based features and does not take context features of pixels into account. This leads to over/under segmentation. In this paper, we present two improvements on KMeans that we call WIKMeans and CIKMeans. The first improvement is on the initiation of seeds based on Wavelet transform. The second one is we integrate context information into feature vector. Both improvements help to decrease computational time while keeping comparable precision to the original algorithms.References
Addison P. S., The illustrated wavelet transform handbook, NapierUniversity, Edinburgh, UK.
Balaji T., Sumathi M., Relational Features of Remote Sensing Image classification using Effective KMeans Clustering, International Journal of Advancements in Research & Technology, Volume 2, Issue 8, August-2013, pp. 103-107.
Chih-Tang Changet al., A Fuzzy KMeans Clustering Algorithm Using Cluster Center Displacement, Journal of Information science and Engineering 27, 2011, pp. 995-1009.
Canada Center for Remote Sensing, Fundamentals of Remote Sensing, http://www.ccrs.nrcan.gc.ca, 2008.
Dubes R. C. and Jain A. K.,Algorithms for Clustering Data, Prentice Hall, 1988.
Hasanien A.E., A. Badr, A Comparative Study on Digital Mamography Enhancement Algorithms Based on Fuzzy Theory, Studies in Informatics and Control, Vol.12, No.1, March 2003.
http://www.onmyphd.com/?p=KMeans.clustering
Mallat S.G.,A theory for multi resolution signal decomposition, the wavelet representation. IEEE transactions on Pattern Analysis and machine Intelligence, 11(7): 674-693, 1989.
Muhammad Amir Shafiq and Saqib Ejaz, Real T ime Implementation of Multilevel Perfect Signal Reconstruction Filter Bank, International Journal of Engineering & Technology IJET -IJENS Vol:10 No:04.
NGUYỄN KHẮC THỜI và cộng sự, Giáo trình Viễn thám, trường Đại học Nông nghiệp Hà Nội, 2011.
Shruti Dalmiya và et al., Application of Wavelet based KMeans Algorithm in Mammogram Segmentatio, International Journal of Computer Application, Volume 52– No.15, August 2012.
Valliammal N., S.N.Geethalakshmi, Leaf Image Segmentation Based On the Combination of Wavelet Transform and K Means Clustering, International Journal of Advanced Research in Artificial Intelligence, Vol. 1, No. 3, 2012.
Meritxell Bach Cuadra, Jean-Philippe Thiran, Satellite Image Segmentation and Classification, Diploma project, Fall 2004.
Intan aidha yusoff, Nor ashidi mat isa, Two-Dimensional Clustering Algorithms for Image Segmentation, WSEAS Transactions on Computers, Issue 10, Volume 10, October 2011.
J. Liu, and Y. H. Yang, Multiresolution color image segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.16, no.7, pp.689-700, Jul 1994.
R. H. Haralick, and L. G. Shapiro, Image segmentations techniques, Computer Vision Graphics Image Processing 29, pp. 100-132, 1985.
http://landsat.gsfc.nasa.gov/wp-content/uploads/2013/01/BandpassesL7vL8_Jul20131.pdf
J.C. BEZDEK, R. EHRLICH, W.FULL, FCM: The fuzzy c-Means clustering algorithm, Computers & Geosciences Vol. 10, No. 2-3, (1984), pp. 191-203.
