Millimeter wave image quality classification model construction method based on local enhancement

The invention provides a millimeter wave image quality classification model construction method based on local enhancement, and the method can enable the definition of a whole image to be improved after the local enhancement of the input image, is higher in discrimination degree with a blurred image, and enables the definition of the blurred image not to be remarkably changed after the enhancementof the blurred image. And for the enhanced image, an effective feature vector is constructed and extracted, and the effective feature vector is sent to a classifier for training. The method has the advantages that the contrast of the clear image and the blurred image is improved through local enhancement, the difference between the two types of images is increased, a feature vector is constructedthrough a direction gradient histogram feature and a gray level co-occurrence matrix feature; the information of the millimeter wave images can be better described, so that after the images are classified, the difference betw