Abstract: In last few decades, Image classification has become one of the extensively used research area due to its wide range of applications like ground water exploration, environmental disaster assessment, terrain feature extraction, urban planning, & land use monitoring etc. There exist various traditional, nature inspired and other classification approaches that are being used for the satellite image classification. But the results obtained from the existing algorithms are nor much efficient to use for any real life application. In this paper, we are applying the swarm intelligence based hybrid approach to classify the land cover features. The algorithms considered for the hybridization are Cuckoo Search (CS) and Artificial Bee Colony Optimization (ABC). As individual algorithm are not much efficient for classification, so hybrid concept is considered to make the classification more efficient and accurate. The output results obtained from the hybrid concept are compared with the individual CS & ABC algorithms. Also some other algorithms like Particle Swarm Optimization (PSO), Biogeography Based Optimization (BBO), hybrid ACO/BBO, hybrid CS/PSO, hybrid CS/ACO and hybrid ABC/BBO are considered for the comparison purpose.
Keywords: Swarm Intelligence, Cuckoo Search (CS), Artificial Bee Colony Optimization (ABC), Remote Sensing, Image Classification.