Method and device for removing glasses from human face image, and method and device for wearing glasses in human face image

Abstract

The invention provides a method and a device for removing glasses from a human face image, and a method and a device for wearing the glasses in the human face image. The removal method comprises the following steps of: acquiring a glasses-worn eye area image and a non-eye area image from a glasses-worn human face image; matching the glasses-worn eye area image by using a classifier to acquire a corresponding eye area type, wherein the classifier is used for multiple types of eye areas which are constructed according to glasses-free human face image samples, and the multiple types of eye areas are classified according to eye shapes; acquiring a base vector corresponding to the eye area type, wherein the base vector is acquired by performing principal component analysis (PCA) study aiming at the sample of the eye area type; mapping the glasses-worn eye area image to the base vector, and reconstructing to acquire a glasses-free eye area image; and splicing the non-eye area image with the glasses-free eye area image to acquire a glasses-removed human face image. By the method, the glasses can be relatively effectively removed from the human face image.

Description

technical field [0001] The present invention relates to the technical field of pattern recognition, in particular to a method and device for removing glasses from a face image, and a method and device for wearing glasses in a face image. Background technique [0002] At present, as an important research field in recent years, face-related technologies such as face recognition and detection and tracking have made great progress. However, in practical applications, many factors such as posture, glasses, expressions, shadows, etc. It has an impact on the recognition effect, among which glasses are a common interference object. [0003] The occluded part of the glasses often contains the feature points required in face recognition, such as the pupil area and the edge of the eyes; some people wear glasses themselves but want to get a pair of contact lenses in the optical shop. Face image processing obtains a face without glasses frame, which helps to improve the accuracy of reco...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that in the face image after the glasses are removed, the face image in the glasses area often leaves traces of the glasses frame, resulting in unnatural joints between the glasses area image and the surrounding face images, because the specific eye size is not considered The difference between the obtained eyes is often distorted, and there is a big gap with my own eye image, so it is not very practical

Images