Man face image identifying method based on man face geometric size normalization

Abstract

The invention relates to a human face image recognizing method based on the geometric size normalization of a human face, belonging to image processing technical field, and comprising the steps of: determining the coordinates of the left and right eyeballs on an input human face image, and according to the coordinates, rotating the image to the horizontal position to obtain a new human face image 2, then determining the coordinates of left and right eyeballs and mandible of the new human face image 2, specifying the numeric value of normalized geometric size of a human face, zooming in or out the new human face 2 to obtain another human face image 3 meeting the standard distance; according to the coordinates of left and right eyeballs and mandible of the human face image 3, cutting the human face image 3 to obtaina standard normalized human face image; forming training-set, known and to-be- recognized human face images into human face images of normalized geometric size and extracting human face characteristics, and in a known human face database, adopting the methods of calculating similarity and sequencing according to the similarity to recognize the human face. The invention obviously improves the visual effect of a human face and makes a higher increase in the recognizing ratio.

Description

technical field [0001] The invention belongs to the technical field of image processing, and particularly relates to a method for improving a face recognition rate. Background technique [0002] Face recognition involves many disciplines, including image processing, computer vision, pattern recognition, etc. It is also closely related to the research results of physiology and biology on the structure of the human brain. The recognized difficulties in face recognition are: [0003] (1) Face changes caused by age; [0004] (2) Face diversity caused by posture; [0005] (3) Plastic deformation of the face caused by expressions; [0006] (4) The multiplicity of face patterns caused by factors such as glasses and makeup; [0007] (5) Differences of face images caused by illumination. [0008] In general face recognition algorithms, there is no normalization of the standard geometric size of the face image, and the normalization of the geometric size will not only affect the ...

AI Technical Summary

Problems solved by technology

[0007] (5) Differences in face images caused by illumination

[0008] In the general face recognition algorithm, there is no normalization processing of the standard geometric size of the face image, and the normalization processing of the geometric size will not only affect the recognition rate of face recognition, but also affect the number of people in the face database. face visual effects

The existing face geometric size normalization method is mainly based on the distance between the two eyes, however, the distance between the two eyes of the face is unstable, especially in the horizontally rotated face image, this Instability is more prominent

Images