A Hybrid Firefly with Particle Swarm Optimization Based Hyperspectral Image Classification and Segmentation Using Structured Support Vector Machine

Nowadays, hyperspectral satellite imaging (HSI) is widely being applied for terrain feature segmentation and classification in the remote sensing domain.However, such automated techniques for accurate segmentation and classification are still significant real-world challenges.To mitigate these challenges, a hybrid Firefly with Particle Swarm optimization (Hybrid FF with PSO) based hyperspectral satellite image segmentation and classification approach is proposed.This approach consists three major steps.At first, hyperspectral satellite images are pre-processed using the median filter to increase image quality and make categorization more efficient.Then, the input data is processed into a gray-level image, which serves as the matrix value for the image during the feature extraction process using a gray-level co-occurrence matrix (GLCM).These extracted images contain pixel values that have been improved classification results using a Hybrid FF with PSO approach.Then, HSI image is segmented using the binary classification procedure with the OTSU's threshold approach.At last, Structured Support Vector Machine (SSVM) with different image classes is used for the classification procedure.This research used datasets from AVIRIS sensor through a flight movement over the Indian pines location in North-western Indian.The simulation outcomes depict the proposed approach obtained superior performance than the conventional approaches in terms of sensitivity, specificity, accuracy, recall, precision, and F1-score.