Total views : 335

Hypergraph-based Algorithm for Segmentation of Weather Satellite Imagery

Affiliations

  • Department of Computer Science, SASTRA University, Thanjavur - 613401, Tamil Nadu, India
  • Department of Mathematics, SASTRA University, Thanjavur - 613401, Tamil Nadu, India

Abstract


Objective: Classification of cloud images through segmentation of automated satellite images to improvise the level of accuracy. Method Analysis: To classify cloud images the hyper graph model uses the idea of maximally bonded subsets that is endowed with integer valued metric are applied to receive the classifications. The widely used hyper graph model is Intensity Neighborhood Hyper graph (INHG) and representation model in this article is Intensity Interval Hyper graph (IIHG). Findings: The results obtained through this process is proved to be more accurate and the time complexity is O(n) in weather prediction. Similarly, the results received through IIHG, which also provides the same computational complexity where all the pixels to be processed with less time. Enhancement: The proposed methodology increases the accuracy level of prediction with less computation time and this work can be enhanced by including pattern recognition in automated processing.

Keywords

Hyper Graph, INHG, IIHG, Satellite Imagery, Segmentation.

Full Text:

 |  (PDF views: 599)

References


  • Peak JE, Tag PM. Towards automated interpretation of satellite imagery for navy shipboard applications. Bulletin American Meteorological Society. 1992; 73(7):995–1008.
  • Peak JE, Tag PM. Segmentation of satellite imagery using hierarchical thresholding and neural networks. Journal of Applied Meteorology. 1994; 33(1):605–16.
  • Joseph SS, Ramu G. Performance evaluation of basic compression methods for different satellite imagery. Indian Journal of Science and Technology. 2015 Aug; 8(19):1–8.
  • Kim D. Integration of near infrared image and probabilistic classifier to increase the classification accuracy of point clouds. Indian Journal of Science and Technology. 2015 Aug; 8(20):1–6.
  • Atif I, Mahboob MA, Waheed A. Spatio-temporal mapping and multi-sector damage assessment of 2014 flood in Pakistan using remote sensing and GIS. Indian Journal of Science and Technology. 2015 Dec; 8(35):1–11.
  • Bretto A, Azema J, Cherifi H, Laget B. Combinatorics and image processing. Graphical Models and Image Processing. 1997; 59(5):265–77.
  • Bretto A, Cherifi H, Aboutajdine D. Hypergraph imaging: An overview. Pattern Recognition. 2002; 35(3):651–8.
  • Bretto A, Gillibert L. Hypergraph-based image representation. Graph-Based Representations in Pattern Recognition. 2005; 3434:1–11.
  • Dharmarajan R, Kannan K. A hypergraph-based algorithm for image restoration from salt-and-pepper noise. AEU International Journal of Electronics and Communication. 2010; 64(12):1114–22.
  • Dharmarajan R, Kannan K. Hypergraph-based segmentation and edge detection in gray images. 2012; 68(2):185–203.
  • Berge C. Hypergraphs - combinatorics on finite sets. North-Holland Mathematical Library, Amsterdam; 1989.
  • Tom M, Apostol A. Mathematical Analysis. 2nd edition, Addison-Wesley Publishing, Reading; 1974. p. 1–256.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.