Hand multimode fast recognition method based on rough sorting

The invention belongs to the field of identity recognition and particularly relates to a hand multimode fast recognition method based on rough sorting. An imaging device is adopted to obtain hand modes for analysis so as to obtain hand shape feature parameters. The method comprises the following steps that (1) a multimode image acquisition device is adopted to obtain three kinds of mode images including a hand shape image, a palm print image and a palm vein image when a hand stretches naturally once; (2) whether an effective region with palm veins exists or not is judged and determined, whether the number of data with the gradient beyond a certain range in the region exceeds a preset threshold value or not is judged, and it is judged that the veins exist in the region if the number exceeds the threshold value and the veins do not exist in the region otherwise; (3) the number of main lines of palm prints and the number of intersections are measured so as to determine a matching object. The hand multimode fast recognition method based on rough sorting is simple in algorithm, high in robustness and stability, high in matching speed, low in false acceptation rate and wide in application range.