Face recognition method and system, and removing method and device for glasses frame in face image

Abstract

The invention relates to a removing method for a glasses frame in a face image. The method comprises the steps of: detecting and positioning eyes in the input face image with a pair of glasses, geometrically correcting the face image on the basis of the positioned result to form a first image; extracting an eye estimation area from the first image to obtain a second image, and conducting mathematical morphology processing on the second image so as to determine the position of a glasses frame; based on the first image, establishing a face skin color model; in the second image, interpolating each pixel point of the glasses frame the position of which is determined, correcting the interpolation result in a part of pixel points of the glasses frame according to the skin color model, and conducting de-noising processing to form a ninth image; and replacing the eye estimation area in the first image by the ninth image, synthesizing and outputting the face image the glasses frame of which is removed. According to the technical scheme, the glasses frame in the face image with a pair of glasses can be conveniently and effectively removed, and the face recognition rate can be further improved.

Description

technical field [0001] The invention relates to the field of image processing and pattern recognition, in particular to a face recognition method and system, and a method and device for removing spectacle frames from a face image. Background technique [0002] As an important identification technology, face recognition has broad application prospects in security, finance, human-computer interaction, information, education and many other fields. The current face recognition system performs face recognition by comparing the template image in the template library with the recognition image (face image) formed by the face to be recognized. recognition effect. However, when there are occluders in the recognition image and the template image is not occluded, the recognition rate will be reduced due to the difference in features between the images. Among them, the occlusion of the glasses is particularly prominent, due to the texture, shape, position, lens color, blur degree and l...

AI Technical Summary

Problems solved by technology

Among them, various glasses detection methods are applied, such as active shape model, snake model, artificial neural network (Artificial Neural Networks), Hough transform and other methods, but the problem with these methods is that they rely too much on The result of glasses detection, and due to the diversity of glasses, it is difficult to meet the requirements of glasses detection itself; the reconstructed image is distorted, and the reconstructed image is composed of training samples linearly, which must be different from the original image; for blurred or reflective lenses and frames The performance of darker colors is poor. There will always be spectacle frames and dark spots in the reconstructed image. Specific glasses-wearing and corresponding non-glasses samples are required for learning.

Images