Efficient Satellite Image Retrieval Using Shearlet Transforms and Spiking Neurons-Based Liquid Autoencoder Model

This paper introduces an innovative content-based image retrieval system for precise and effective retrieval of satellite images. The system integrates liquid autoencoders with shearlet transforms to derive robust feature representations from satellite images. Empirical results demonstrate that the proposed system achieves a high retrieval accuracy of more than 95% on different datasets and is comparable with several state-of-the-art approaches. The efficiency of the system is further indicated by its fast inference time and moderate memory needs, making it suitable for large image databases. This study contributes to the literature on satellite image analysis by introducing a valid tool for several applications, including environmental monitoring and land-use mapping. The new method contributes value to the existing literature in Content-based image retrieval by showing the suitability of liquid autoencoders for satellite image retrieval.