A face multi-attribute recognition method based on multi-source data

Abstract

The invention belongs to the technical field of face attribute recognition, in particular to a face multi-attribute recognition method based on multi-source data. Aiming at the problem that a single face attribute data set often contains limited attribute labels and often cannot meet the labeling requirements for all attributes in the multi-attribute recognition task, the invention proposes a face multi-attribute recognition method based on multi-source data. The specific requirements of the face attribute recognition task can be combined with multiple existing data sets to meet the multiple attribute labeling requirements required by the task, and through joint training, multiple data sets can promote each other, and the face The attribute recognition network is effectively trained, so as to realize the joint recognition of various attributes of the input face image. The beneficial effect of the invention is that, while satisfying all attribute labeling requirements of the task, the information interaction between multiple attributes is realized through the mutual cooperation of multiple data sets, the joint training objectives of multiple attributes are completed, and the network generalization effect is improved.

Description

technical field [0001] The invention belongs to the technical field of face attribute recognition, in particular to a face multi-attribute recognition method based on multi-source data. Background technique [0002] With the rapid rise of artificial intelligence and the continuous development of image acquisition and processing technology, artificial intelligence applications for information mining and utilization of images can be seen everywhere in people's lives. As an important biological feature, human face contains a lot of important information, and it is more and more favored by researchers because of its rich details and easy access. [0003] The initial research on face data is face recognition and face detection, which is the most direct application of face information. With the continuous growth of people's material and cultural needs, researchers are also constantly developing the use of face information, and face attribute recognition has emerged as the times r...

AI Technical Summary

Problems solved by technology

[0006] In addition, with the continuous expansion of the demand for face attribute research, some problems have been exposed in the current face attribute data set, which seriously hinders the research progress in this direction.

For example, the category distribution of the data set is unbalanced, or for multi-attribute recognition tasks, a single data set cannot provide all attribute labels, etc.

Images