LAND USE AND LAND COVER CLASSIFICATION FOR VISAKHAPATNAM USING FUZZY C MEANS CLUSTERING AND ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM

In current decades, Land Use (LU) and Land Cover (LC) classification is the most challenging research area in the field of remote sensing. This research helps in understanding the environmental changes for ensuring the sustainable development. In this research, LU and LC classification assessed for Visakhapatnam city. After collecting the satellite images, Hybrid Directional Lifting (HDL) technique was used to remove the saturation and blooming effects in the input images. The pre-processed satellite images were used for segmentation by applying Fuzzy C means (FCM) clustering. Then, Local Binary Pattern (LBP) and Gray-level co-occurrence matrix (GLCM) features were utilized to extract the features from the segmented satellite images. After obtaining the feature information, a multi-class classifier: Adaptive Neuro-Fuzzy Inference System (ANFIS) was used to classify the LU and LC classes; water-body, vegetation, settlement, and barren land. The experimental outcome showed that the proposed system effectively distinguishes the LU and LC classes by means of sensitivity, specificity, and classification accuracy. The proposed system enhances the classification accuracy up to 7% compared to the existing systems