Satellite image detection and classification using hybrid segmentation and feature extraction with enhanced probabilistic neural network

Satellite Image Processing is a vital field of research and development that involves the processing of images of the Earth and satellites obtained by artificial satellites. Images are digitally taken before being analyzed by computers to get information. Due to image format inadequacies and defects, data received from imaging sensors on satellite platforms includes deficiencies and errors, necessitating additional activities to improve image quality. The massive network of remote sensing satellites circling the Earth provides comprehensive and periodic coverage of the Earth, enabling a wide range of uses for human benefit. Before being applied to the kernel fuzzy C-means algorithm with spatial information with Penguin search Optimization (SKFCM with PeSOA) segmentation step, the image data is pre-processed. To extract a collection of features from the segmented nucleus, hybrid feature extraction is performed. In this hybrid approach, the discrete wavelet transform with gray-level co-occurrence matrix (DWT with GLCM) algorithm was used. The attributes that have been segmented and retrieved are utilised to train the Enhanced Probabilistic Neural Network classifier. Metrics such as accuracy, f-measure, specificity, and sensitivity are used to assess classification efficiency. When compared to other classifiers, the Enhanced Probabilistic Neural Network classifier has 98.1 percent accuracy.