Image identification method, related device and identification system

Abstract

The embodiment of the invention discloses an image identification method, a related device and an identification system. An image identity recognition method may include: performing feature extraction processing on a face image to be identified to obtain an available integrated feature vector corresponding to the face image to be identified; based on the available integrated feature vector corresponding to the face image to be identified Calculate the identity feature vector corresponding to the above-mentioned face image to be identified; calculate the similarity between the identity feature vector corresponding to the above-mentioned face image to be identified and the identity feature vector corresponding to each sample face image in the Z sample face images degree; output the identity information corresponding to Z1 sample face images. The solution of the embodiment of the present invention is beneficial to improve the accuracy and versatility of image identification, and further satisfy the requirements of more application scenarios as much as possible.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image identification method, a related device and an identification system. Background technique [0002] Image-based face recognition has a wide range of applications in the fields of personal identification, finance, security systems, and data identification. As people age, the face undergoes changes in contour, pigmentation and texture. For example, aging people generally show wrinkles, hyperpigmentation, etc. These age-related changes make matching faces of different ages very challenging. figure 1 Examples are shown of photos of the same person at different ages, and it can be seen that the faces of the same person at different ages have certain differences. [0003] An existing popular technology is based on a generative model for face recognition. Its core idea is to establish a generative model to simulate the aging process of the face. The specific method ...

AI Technical Summary

Problems solved by technology

[0004] During the research and practice of the existing technology, the inventors of the present invention found that although the above-mentioned existing algorithm has achieved certain effects, it has the following limitations. First, it is very difficult to construct such a generative model, because the human face The aging process is very complex, involving many factors such as human physiology, psychology, genetics, living and working habits, life experience, etc. It is difficult to accurately express it with a fixed aging model

Moreover, in many cases, the age compensation effect is not good, but a lot of noise is introduced, which has a negative effect on the later recognition.

In addition, this type of algorithm requires some extra information such as the age information of the face, but this information is often lacking in many applications

Therefore, the effectiveness and applicability of such algorithms are subject to many restrictions.

Images