Human face aging analogue method based on face super-resolution process

Abstract

The invention discloses a human face aging simulating method based on human face super-resolution treatment. The method comprises the following steps: normalizing a human face image; training a super-resolution method for each age bracket; reducing the resolution of each inputted image; and performing the human face super-resolution treatment for an appointed age bracket, i.e. utilizing the trained human face super-resolution method to fill face venation information on the appointed age into the inputted face image with low-absolution so as to obtain a human face aging simulation image. The available human face super-resolution method is a human face super-resolution method based on learning. The invention adopts eigentransformation, can be applicable to any human face super-resolution methods based on the learning, utilizes the human face super-resolution based on the learning and can genuinely and believably simulate human face aging; and the invention only takes the change of human face venation, so the calculation is fast.

Description

technical field [0001] The invention relates to a face aging simulation method based on face super-resolution, belonging to the technical field of pattern recognition. Background technique [0002] Among the various factors that affect the accuracy of face recognition, posture, expression, and lighting are all external factors. Relatively speaking, there are many more mature methods to solve them, and the impact of age changes is the change of the individual itself. The resulting features are so varied that they cannot be identified. The face aging simulation method can realize the automatic update of the face database to enhance the robustness of the face recognition system, and can also be used in the field of finding missing persons and electronic entertainment. [0003] Designing and implementing a mature and reliable face aging simulation and age recognition algorithm has many practical significance: [0004] The specific facial features of a particular individual can...

AI Technical Summary

Problems solved by technology

In most cases, whether it is qualitative or quantitative, the simulation results are better than the traditional PCA method, but the ideal effect cannot be achieved for individuals who are not similar to any individual in the training library, such as: different races from the training library and some Occlusion

Narayanan Ramanathan and RamaChellappa proposed a craniofacial growth model that can simulate the growth process of the human face from infancy to adulthood. This model is inspired by the "cardioidal strain" and uses markers to define the shape information collected during the growth process of the human face. , using linear and nonlinear constraints to express the face aging process. According to the experimental results, this method can better solve the problem of face aging simulation from childhood to adulthood; but this method does not take grayscale, texture, etc. into account feature

Images