Method of face detection and face comparison

Abstract

The invention discloses a method of face detection and face comparison. The method of face detection and face comparison includes inputting of images, calculation of characteristics, and outputting oftypes, and has the advantages that the face characteristic identification system used in inputting of images has preferable isolation and interactivity, and the detected person can obtain a face image of the detected person without directly contacting a detection unit, and the requirement for equipment and mounting is not high; the calculation characteristics can enable the system to automatically complete detection and identification through a preset method while the whole process does not need manual operation and does not need direct participation of the detected person, thus realizing omnibearing intelligentization; the key points in the step 3 include the position of the canthus, the position of the nose, the contour points of the face, and the like, so that calibration can be performed on the face and the error caused by non-use of posts can be eliminated; and in the step 4, different face images have different vectors, and the distance expressed by the vectors can directly reflect the similarity of the faces, thus being convenient for comparing the faces.

Description

technical field [0001] The invention relates to a face recognition method, in particular to a face detection and face comparison method, and belongs to the technical field of biological feature recognition. Background technique [0002] With the rapid development of modern information technology and the urgent need for fast and effective automatic self-verification in all aspects, biometric identification technology has developed rapidly in recent decades. Line biotechnology is mainly through the close combination of computer and high-tech means. , using the inherent physiological characteristics and behavioral characteristics of the human body to identify personal identities, which has strong self-stability and individual differences. Biometric technology does not need to be changed frequently like a password, and it is not easy to forget, and it is not like a fixed password. The object itself is worried about being stolen and lost by others. Therefore, biometric technology...

AI Technical Summary

Problems solved by technology

[0003] Face recognition technology combines the theories and methods of digital image processing, computer graphics, pattern recognition, computer vision, artificial neural network, biometric technology, physiology, psychology and other disciplines. Great progress has been made, but the current technology still cannot effectively process and automatically track faces in complex backgrounds.

Therefore, face recognition technology is still a challenging topic at present and for a long time in the future.

Images