Palms　alignment　is　an　important　work　for　palmprint　recognition　in　uncontrolled　environment.　Many　methods　have　made　progress　to　achieve　alignment.　But　most　of　them　ignore　the　palm＇s　angles,　which　could　not　satisfy　the　alignment　initialization　when　the　hand　has　a　large　in-plane　rotation.　In　this　paper,　we　propose　a　palms　alignment　with　affine　transformation　method　based　on　a　two-stage　convolutional　neural　network　(CNN).　The　basic　idea　is　to　rotate　the　target　palm　into　the　same　angle　category　to　avoid　the　following　affine　registration　has　a　big　matching　error　at　the　beginning.　At　the　stage　I,　the　given　target　palm　is　classified　into　two　angle　categories.　At　the　stage　II　the　upside　down　palm　is　firstly　rotated　180　degrees,　and　then　inputted　into　the　subsequent　feature　extraction　network,　feature　matching　layer　and　regression　network　to　achieve　the　affine　alignment.　Experimental　results　have　proved　the　effectiveness　of　our　method.　©　2020　IEEE.