SIFT　algorithm,　with　its　features　invariant　to　image　scaling,　rotation　and　illumination,　has　been　widely　adopted　in　image　matching.　In　order　to　improve　the　efficiency　of　image　matching　and　operation　in　different　scales　and　different　resolution,　this　paper　has　utilized　adaptive　threshold　to　eliminate　unstable　keypoints.　And　a　transform　based　on　the　weighted　least　square　is　adopted　to　filter　the　matching　point　pairs　to　reduce　outliers.　Experiments　show　that　the　proposed　method　has　better　precision　and　stability　than　other　improved　matching　algorithms.　©　2012　IEEE.