Single-sample human face recognition method compatible for human face aging recognition

Abstract

The invention provides a single-sample human face recognition method compatible for human face aging recognition, which comprises the steps of conducting the aging simulation on the pre-stored image model of a human face sample to re-construct the image model of the human face sample; conducting the global feature matching for a to-be-recognized human face image model with the image model of the human face sample, wherein if the matching fails, regarding the recognition result as mismatching; and conducting the local feature matching for the to-be-recognized human face image model with the image model of the human face sample, wherein if the matching fails, regarding the recognition result as mismatching. The above to-be-recognized human face image model is an active appearance model of a to-be-recognized human face image. The image model of the human face sample is an active appearance model of a reserved human face sample image. According to the technical scheme of the invention, the recognition effect compatible for human face aging influence is realized and improved based on the combination of the AAM technique with the IBSDT technique. Meanwhile, based on the combination of the AAM technique with the triangulation matching technique, the matching reliability of global features is greatly improved. Based on the combination of the LBP technique with the SURF technique, the matching reliability of local features and the illumination robustness are improved. Finally, the high recognition rate for the reserved human face image as a single sample is realized.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a single-sample face recognition method compatible with face aging recognition. Background technique [0002] Face image processing and recognition is an important research topic in the field of computer vision and image processing, and has been concerned by many researchers. In criminal investigation, medical treatment, entertainment, information, space and other fields, the processing and transformation of portraits has a wide range of application requirements. [0003] The age of a person is a long-term process that changes over time, which will cause relatively obvious changes in the external appearance of the face. In the face recognition system, it is not only necessary to solve the problems of noise and distortion in the face images of the same person in the same period, but also to solve the face images taken by the same person in different periods (the span may...

AI Technical Summary

Problems solved by technology

But because the grayscale texture information is not considered, the promotion and application are not good

[0006] Second, 1991-1997: At this stage, the famous FERET face recognition algorithm test and some commercial face recognition systems appeared; face recognition algorithms mainly focused on two-dimensional face linear subspace analysis and statistical pattern recognition etc., for example: Eigenface method (PCA) and Fisherface method (LDA) are still commonly used mainstream algorithms in the field of face recognition until now, but they are mainly used for diverse face recognition; Elastic Graph Matching (EGM) uses attribute graphs to describe people. Face can be used for single-sample face recognition, but due to a large amount of data and complex deformation comparison, the time and space complexity is high, making its applicability worse; active shape model ASM and active appearance model AAM are based on statistics The description method can be used for face recognition. ASM only statistically models the sample shape, while AAM not only establishes a shape statistical model, but also establishes a global texture change model, which is widely used in target detection, recognition, attitude correction and other fields.

[0009] First, the shape of the face is unstable, which will produce various expressions. Moreover, it is easy to produce different visual imaging effects when viewed from different angles, which brings challenges to the stability and accuracy of face recognition.

[0010] Second, aging changes occur in facial features as we age

[0012] Fourth, for the same algorithm, when the number of training samples is reduced, the recognition accuracy may also drop significantly, so the difficulty of single-sample recognition is particularly prominent

[0013] It is worth noting that for commercial face recognition systems, in many cases, a variety of the above-mentioned negative influencing factors may appear at the same time, affecting the recognition accuracy of the entire system

Images