face recognition method

Abstract

The present invention provides a face recognition method, comprising the following steps: S1: generate a face elastic beam map; S2: generate a face recognition model based on appearance, calculate and obtain the face recognition model based on appearance and the existing face recognition model in the database Cosine similarity between face model vectors; S3: Generate a face recognition model based on geometric features, and calculate the cosine similarity between the face recognition model based on geometric features and the existing face model vectors in the database; S4: Based on the similarity level of step S2 and step S3, use logistic regression to mix; S5: Determine the face recognition result based on the result of step S4. The present invention adopts the face recognition method which mixes the face recognition method based on the appearance and the face recognition method based on the geometric feature at the similarity level, and can be satisfactorily applied in the actual living environment.

Description

technical field [0001] The invention relates to a face recognition method. Background technique [0002] Face recognition technology has developed rapidly in the past few years. At present, face recognition technology cannot be successfully used in real life environments such as outdoor environments, and is only used indoors. The difficulty of face recognition is still lighting changes, posture changes, age changes, occlusion, etc., which have an impact on the face recognition algorithms adopted by the face recognition system, and their degrees vary. The classification of face recognition methods and their advantages and disadvantages The face recognition difficulties that affect this are as follows: [0003] The appearance-based face recognition method uses the pixel values ​​of the face image pixels to generate a face template; the face recognition method based on geometric features does not rely on pixels, but is based on the feature points of the face (eyes, nose, mouth...

AI Technical Summary

Problems solved by technology

The global face recognition method that examines the overall face image has the advantages of expressing both local and global features of the face, but has the disadvantage of being unable to cope with pose changes. On the contrary, the local face recognition method is more sensitive to pose changes than the global face recognition method. Strong, has the advantage of being able to reflect the local characteristics of the face well

[0006] In the past, Elastic Bunch Graph Matching-EBGM (Elastic Bunch Graph Matching), as a face recognition method based on feature points, belongs to the local face recognition method and is one of the most successful face recognition methods, but the local face recognition method The disadvantage is that it cannot reflect the global characteristics of the face

In order to overcome this, a method combining the global face recognition method and the local face recognition method has appeared, which has brought some performance improvements. Both methods are based on the appearance-based face recognition method, which cannot overcome the shortcomings of the appearance-based recognition method. shortcoming

[0007] In the real life environment, face images are difficult to recognize due to changes in lighting, posture, age, occlusion, etc.

Therefore, in the actual living environment, face recognition technology cannot be satisfactory, so in-depth research

In recent years, a lot of research has been done in this field, and great progress has been made, but it is still not satisfactory

Images