This paper presents a scheme for the classification of multispectral satellite images into multiple predefined land cover classes. The proposed approach results in a fully automatic classification model to assign each pixel in the image to a group of pixels based on reflectance or spectral similarity where each subset of group of pixels is called ground-truth data. The input image is preprocessed and applied to a classifier. The proposed supervised classifier incorporates both spectral and spatial information. We implement QDA Classifier (Quadratic Discriminant Analysis) based on spectral features. The classified image is then post processed using Probabilistic Label Relaxation algorithm for smoothening the output image which gives better results. The QDA Classifier uses statistical classification to separate measurements of two or more classes of objects or events by a quadric surface. It estimates the probability of each class across the spectral domain that it takes into account the correlations of the data set from the class centroid. An experiment on multispectral satellite images shows the accuracy of the method.
An authentic personal identification infrastructure is required to control the access in order to secure areas or materials. Biometric technology is based on physiological or behavioral characteristics of a human body. Iris recognition system consists of image acquisition, localization, normalization, features extraction and encoding, and classification. Iris images are downloaded from CASIA Iris V1.0 database for study. To separate the iris region from the eye image, Hough transform is used. Circular Hough transform is used to localize circular iris and pupil region while parabolic Hough transform is used to enhance the occluding eyelids and eyelashes. Daugman"s rubber sheet model is used to normalize the extracted iris region into a rectangular block with constant polar dimensions. After normalization, 2D Gabor filter is employed to extract the important features from iris. Iris provides texture information which is unique, universal and contains high randomness. Feature extraction is performed by convolving the normalized iris region with 2D Gabor filter which gives the phase information. The phase data represented by a data set is utilized as input for classifiers. The classifiers used in this study are Artificial Neural Networks (ANN) and Support Vector Machines (SVM). This study shows that Support Vector Machines gives higher recognition rate than Artificial Neural Networks.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.