Video sequence face identification method based on AAM model

Abstract

The invention discloses a video sequence face identification method based on an AAM model. The method comprises the training step (1) and the identification step (2), wherein the training step (1) comprises PCA protection and (1-2) LDA protection, projection is carried out on feature vectors which are subjected to dimensionality reduction of the PCA protection through a WLDA, and therefore the best classification feature of each training picture is obtained; the identification step (2) comprises (2-1) Adaboost detection, (2-2) AAM tracking and gesture correction, (2-3) PCA projection, (2-4) LDA protection aiming to obtain the best classification feature of a face picture to be identified, (2-5) nearest-neighbor classifier decision which judges the face picture of types where gamma1 is located to the be the identification result, and the gamma1 is the smallest euclidean distance between the best classification feature of the face picture to be identified and the best classification feature of all training pictures. The video sequence face identification method has the advantages of being capable of accurately identifying a face under the condition that the face gesture is variable, and is strong in robustness.

Description

Technical field [0001] The invention relates to a face recognition method, in particular to a video sequence face recognition method based on an AAM model. Background technique [0002] In this era of information expansion and rapid development of computer technology, humans have begun to hope that computers will become a machine that can communicate with each other in natural language, and are eager to develop new concepts of human-machine interface and artificial intelligence technology, so that people can not Then rely on the traditional computer keyboard, mouse and display equipment and other interactive equipment. However, to achieve such a natural human-computer interaction requires the computer to accurately and quickly obtain the user's identity, status, intention and related characteristic information. Since the large amount of information contained in the human face is an important information transmission window, the computer uses the uniqueness of the human face to o...

AI Technical Summary

Problems solved by technology

However, in the video sequence, the current face recognition method must cooperate with the user to achieve the ideal recognition effect. If the user does not cooperate during the recognition process, the recognition effect may be greatly reduced.

In addition, in the video sequence, due to the changeable face posture, etc., the recognition rate of these methods has decreased to varying degrees.

Images