Cryo-EM detects protein conformations froze in solution, and thus provides a promising way to characterize these conformational changes. In order to detect the conformational change, we developed a new algorithm to obtain multiple conformations and their populations from Cryo-EM datasets. In our algorithm, we constructed our “basis set” (as templates) by applying Molecular Dynamics (MD) simulations to widely search the conformational space, and then perform the fast assignment of experimental Cryo-EM 2D images to a set of reference 2D images generated by these basis-set structures. We find that our algorithm holds promise to be widely applied to elucidate the dynamic ensemble of protein conformations from Cryo-EM datasets.