Satellite Remote Sensing Image Based Aircraft Recognition Using Transform Features And Detect FDCT Using OTSU Segmentation

This project presents the Recognition of object (Aircraft) in an image for better recognition based on the combination of wavelet features and correlation on shape analysis. An object can also be recognized with help of texture or appearance features through Scale invariant feature transform (Wavelet Transform). These correlation measurement and SIFT for appearance feature extraction are effectively utilized for accurate object recognition. Along with this system, Gaussian noise features removal also used to extract the minimal luminance changes from images for better performance. These techniques are useful to minimize the drawback of previous methods like texture features and OTSU (Multi Scale segmentation) .Aircraft on the wavelet based method, we propose a new hybrid recognition method that combines Wavelet features and Correlation changes. Here, Gaussian noise removal purpose we will use filter process and feature extraction purpose we use wavelet transform Each sub band can vary in the number and the types of features, where these two degrees of variability empower the hybrid method with even more flexibility and discriminative potential on recognition on aircraft. The performance of these used algorithms will be differentiated though precision and recall rate metrics. These results show the proposed shape primitives are indeed sufficiently powerful to aircraft recognize in satellite remote sensing images. Keywords—Template Matching; otsu; dwt; fdct; sift; hog; Haar Transform; Segmentation