High resolution reconstruction method of ghost imaging via SURF-NSML

To meet the visual characteristics of human eyes, high resolution imaging technology came into being. In this paper, a high resolution reconstruction method of ghost imaging via SURF-NSML is proposed. Using the image registration method of Speeded Up Robust Features (SURF) and the fusion algorithm of New Sum of Modified Laplacian (NSML), a series of low-resolution images obtained by the ghost imaging system were registered and fused to obtain high-resolution images. This high resolution image reconstruction method does not need the use of spectroscopic devices, filters and other devices, simplifying the experimental equipment; and it is received by a bucket detector, which greatly increases the utilization of experimental equipment. By the reconstruction analysis of images from natural scenes and from the medical field, it is proved that this method combining the device platform with the language algorithm can reconstruct the target image with better visual characteristics and richer details, which has a good promotion effect on the research of image reconstruction.