ABSTRACT

Widely used Bayesian classifier is based on the assumption of equal prior probabilities for all the classes. However, inclusion of equal prior probabilities may not guarantee high classification accuracy for the individual classes. Here, we propose a novel technique - Hybrid Bayesian Classifier (HBC), where the class prior probabilities are determined by unmixing a supplement low spatial-high spectral resolution multispectral (MS) data that are assigned to every pixel in a high spatial-low spectral resolution MS data in Bayesian classification. This is demonstrated with two separate experiments – firstly, class abundances are estimated per pixel by unmixing MODIS data to be used as prior probabilities while posterior probabilities are determined from the training data obtained from ground. These have been used for classifying the IRS LISS-III MS data through Bayesian classifier. In the second experiment, abundances obtained by unmixing Landsat ETM+ are used as priors and posterior are determined from the ground data to classify IKONOS MS images through Bayesian classifier. The results indicated that HBC systematically exploited the information from two image sources improving the overall accuracy of LISS-III MS classification by 6% and IKONOS MS classification by 9%. Inclusion of prior probabilities increased the average producer’s and user’s accuracy by 5.5% and 6.5% in case of LISS-III MS with 6 classes and 12.5% and 5.4% in IKONOS MS for the 5 classes considered.   

Index Terms— prior probability, unmixing, Bayesian classifier