Wyniki wyszukiwania - BazTech

Ograniczanie wyników

1 Foundations of Computing and Decision Sciences

1 2009

Powiadomienia systemowe

Sesja wygasła!

Znaleziono wyników: 1

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: cluster validity measures

Sortuj według:

Ogranicz wyniki do:

A new multiobjective simulated annealing based fuzzy clustering technique: application to automatic pixel classification in remote sensing imagery

Saha S., Bandyopadhyay S.

Foundations of Computing and Decision Sciences

2009

Vol. 34, No. 3

209-229

An important approach for landcover classification in remote sensing images is by clustering the pixels in the spectral domain into several fuzzy partitions. In this article the problem of fuzzy partitioning the satellite images is posed as one of searching for some suitable number of cluster centers so that some measures of validity of the obtained partitions should be optimized. Thus the problem is posed as one of multiobjective optimization. A recently developed multiobjective simulated annealing based technique, AMOSA (archived multiobjective simulated annealing technique), is used to perform clustering, taking two validity measures as two objective functions. Center based encoding is used. The membership values of points to different clusters are computed based on the newly developed point symmetry based distance rather than the Euclidean distance. Two fuzzy cluster validity functions namely, Euclidean distance based well-known XB-index and the newly developed point symmetry based FSym-index are optimized simultaneously to automatically evolve the appropriate number of clusters present in an image. The proposed algorithm provides a set of final non-dominated solutions. A new method of selecting a single solution from this final Pareto optimal front is also developed subsequently. The effectiveness of this proposed clustering technique in comparison with the existing Fuzzy C-means clustering is shown for automatically classifying one artificially generated, three remote sensing satellite images of the parts of the cities of Kolkata and Mumbai.