Due to its spectral properties, hyperspectral imaging is superior to other imaging tools in detecting and classifying objects. Hyperspectral imaging instruments can detect light reflected from wavelengths between infrared and ultraviolet, apart from the wavelength the human eye can distinguish on the electromagnetic spectrum. While this feature provides detailed information about the spectral feature of the object under investigation, it causes its spatial resolution to be low due to the

more »

... al trade-off between spatial resolution and spectral resolution. Nowadays, applications of hyperspectral images are increasing in essential fields such as agriculture, mining, medicine and pharmacy, and military purposes. In order for applications to produce more precise results, high spatial resolution is required with high spectral information. Hardware solving of low spatial resolution problems is a costly and challenging method. Therefore, software solution is an interesting area in image processing. In this paper, a hybrid application based on deep learning and sparse representation is applied to increase the low spatial resolution of hyperspectral images. First the application obtains a super-resolution image from a single hyperspectral image with a low spatial image with a deep convolutional neural network. Later, the super-resolution image obtained, and the original low-spatial-resolution hyperspectral image are fused with the dictionary learning method, resulting in a new super-resolution image with high spectral and spatial resolutions. The application results show that our algorithm achieves successful results compared to other super-resolution applications in the literature.