医疗床

Face image local enhancement method based on multi-feature fusion

The invention discloses a face image local enhancement method based on multi-feature fusion. The method comprises the following steps: establishing a face image training set; performing face detection, face alignment and face segmentation on each image in the face image training set to obtain each segmented image; obtaining a segmented biased face image set, and determining the area proportion similarity of each image in the segmented biased face image set, the length-width ratio similarity of each image in the segmented biased face image set, and the face similarity of each image in the segmented biased face image set; carrying out weighted fusion on the three features to obtain a multi-feature fusion template coefficient; and determining an average face contour template according to the face contour template, and obtaining a face image after local image enhancement in combination with the image of the face to be recognized. According to the method, a face segmentation step in face image ...