@article{oai:u-ryukyu.repo.nii.ac.jp:02001972, author = {Mendoza, Noel and Chen, Yen-Wei and Nakao, Zensho and 陳, 延偉 and 仲尾, 善勝}, issue = {61}, journal = {琉球大学工学部紀要}, note = {This paper considers the problem of reconstructing a high-resolution image from multiple under-sampled, shifted and noisy low-resolution frames. Using a hybrid evolutionary algorithm we attempt to reconstruct the original high-resolution image from a sequence of images corresponding to the same scene but shifted by unknown values in both scalar directions and degraded by Gaussian artifacts. The algorithm is easy to implement and can exploit subtle subpixel variations. It can obtain lossy, much more acceptable results than ordinary interpolation. This is exemplified by comparing results with those obtained through conventional interpolation., 紀要論文}, pages = {69--77}, title = {A Hybrid EA Approach to Multisensor Image Superresolution} }