New M.E.Thesis Submitted from cse student

SATELLITE IMAGE CLASSIFICATION BY HYBRIDIZATION OF FPAB ALGORITHM AND BACTERIAL CHEMOTAXIS By Loveleen Kaur,cse


Abstract
Bacterial Foraging Optimization (BFO) has been widely accepted as a global optimization technique. This technique is proposed by K.M. Passino in 2002 to handle complex problems of the real world. In this work, we aim to classify the satellite image using the technique of Bacterial Foraging Optimization. One key step in BFO is the computational chemotaxis, where a bacterium takes steps over the foraging landscape in order to reach regions with high nutrient content. The chemotactic movement of a bacterium may be viewed as a guided random walk. In this thesis work, we design a new algorithm which is based on Bacterial Foraging Optimization which is used to classify the satellite image. The proposed algorithm has been applied to the 7-band satellite image of Alwar region of Rajasthan. Firstly we use a swarm data clustering method based upon flower pollination by artificial bees (FPAB) to cluster the satellite image pixels. Those clusters will be further classified using BFO. This new method shows an improved highly accurate results for the classification of satellite image. The accuracy of the results has been checked by obtaining error matrix and the KHAT statistics of the proposed algorithm. The accuracy of each feature has also been obtained by calculating the producer’s and user’s accuracy. The results indicate that highly accurate land cover features can be extracted effectively when the proposed algorithm is used.


Leisure Readings :