Artificial bee colony algorithm for classification of remote sensed data

This study is to classify satellite data based on traditional swarm intelligence technique. Attempts to classify remote sensed data with traditional statistical classification technique faced number of challenges as the traditional per-pixel classifier examine only the spectral variance ignoring the spatial distribution of the pixels, corresponding to the land cover classes and correlation between bands causes problems in classifying the data and its result. Hence in this work, we use artificial bee colony to improve the performance of classification of data, based upon swarm intelligence to characterise, spatial variations within imagery as a means of extracting information forms on the basis of object recognition and classification in several domains avoiding the issues related to band correlation. The results show that ABC algorithm brings improvement of 5% achieved in overall classification accuracy at 6 classes on comparison with MLC.