Face beauty prediction method based on multi-task transfer learning

Abstract

The invention provides a face beauty prediction method based on multi-task transfer learning, and the method comprises the steps: building a multi-task face database, carrying out the feature learning, carrying out the feature fusion, and building a face beauty prediction model. The method improves the accuracy of face beauty prediction through improving the expression recognition and age recognition. In order to avoid over-fitting of a deep network trained by a small amount of sample data and insufficient computing equipment, a VGG, ResNet and GoogleNet backbone deep convolutional network isused as a shared feature learning network structure, model migration is used, and the trained convolutional network is used to train a migratable shared feature. Network parameters are shared among tasks in the training process, and shared characteristics are learned, so that the accuracy of single task learning of the network is improved. Through using the deep learning network for multi-task learning, the shared representation layer can enable the tasks with universality to be better combined with the correlation information, and the task specific layer can independently model the task specific information.

Description

technical field [0001] The invention relates to the technical field of face beauty evaluation using image processing and machine learning technology, in particular to a face beauty prediction method based on multi-task transfer learning. Background technique [0002] It is human nature to love beauty, and everyone has the heart to love beauty. Aristotle said: "A beautiful face is a better testimonial". The favorable impression of beauty exists in daily life and has a great influence on people's daily life. Research on the beauty of human face is a frontier topic in the research on the nature and laws of human cognition that has emerged in recent years. Exploring how to better measure beauty will help to obtain scientific, objective and quantifiable human face beauty codes, an eternal theme of human beings. The description of human face beauty has made great progress in the interdisciplinary field of human face beauty research. [0003] In real life, people have different ...

AI Technical Summary

Problems solved by technology

However, the use of deep learning methods for face beauty research requires a large number of training samples, and the existing databases for face beauty prediction research are generally small, so it is not only difficult to directly train a deep network model, but also prone to overfitting problems. The existing face beauty evaluation can only be predicted based on a single task, but the evaluation of face beauty is affected by many factors, resulting in inaccurate face beauty evaluation and little reference value

Images