Frogman recognition method

The invention provides a frogman recognition method. The method includes the steps that a frogman image is subject to preprocessing, characteristic extraction and target recognition; the frogman image is subject to noise removing and target segmentation, the frogman image after segmentation is subject to morphological operation, the processed image is subject to connected region marking, the area of each connected region after marking is calculated, small regions with small areas are removed, each remaining connected region of the frogman image after small-area region removing can be mapped to an original gray image, and therefore gray segmentation of the original gray image can be achieved. In this way, a frogman can be effectively separated from the original image.