Novel ANFIS Net for Classifying features from Remotely Sensed Images

This article presents a novel adaptive neurofuzzy inference system (ANFIS) net that is designed to classify dust, clouds, water and vegetation features from remotely sensed images. This system can reestablish the architecture of the ANFIS net according to a linear combination among the kind of membership function (MF), the number of MF, and number of epochs in automatic way. The proposed system is trained on the features of the provided images using eight kinds of MFs, and is designed to find the best ANFIS net that has the ability to have the best classification on data is not included in the training data. This system shows an excellent classification of test data that is collected from the training data. The performances of the best three MFs are %98.95, %98.72 and %98.62 for test data that is not included in the training data. Although, the proposed system was trained on data selected only from one image, this system shows correctly classification of the features in the all images. The designed system can be carried out on remotely sensed images for classifying other features.