Face attribute recognition method and apparatus based on combined depth neural network

Abstract

The invention provides a face attribute recognition method based on a combined depth neural network. The method comprises the following steps: S1, performing area extraction on an inputted face image;S2, carrying out positioning on a facial important part and extracting a related area based on the area extraction result to obtain facial area features and facial key part features; S3, marking a real age and a gender of each face by using the area extraction result as a training sample, carrying out training based on a deep neural network, and outputting an age estimation value and a gender recognition result; and S4, on the basis of the facial area features outputted by the S2 and local area features of eyes and mouths, outputting expression and wearing prediction probabilities respectively according to a random forest algorithm, adding probabilities of corresponding attributes for different attributes, and outputting facial expression and wearing attribute results. In addition, the invention also provides a face attribute recognition apparatus based on a combined depth neural network.

Description

technical field [0001] The invention belongs to the technical field of image recognition of artificial intelligence, and relates to a face attribute recognition method and device based on a combined deep network. Background technique [0002] With the development of society and the advancement of science and technology, face attribute recognition has become more and more widely used in many enterprises and institutions such as finance, military, medical care, and public security. Biological characteristics are specific intrinsic attributes of human beings. Due to their complex structure, many changes in details, and certain individual differences and stability, they can be used as a reliable basis for identity verification. The face is a very important biological feature, which can represent human emotions, gender, age and other attributes. Compared with other human biological features, the acquisition of the features of the face is more direct and imperceptible. The most n...

AI Technical Summary

Problems solved by technology

The first type of method relies too much on experience, is not suitable for multi-source big data processing, and has poor universality. After the emergence of deep learning technology, it has been rarely used.

Although deep convolutional neural networks are widely used today, their accuracy depends on the amount of sample data, and it is difficult to obtain ideal results in the case of insufficient samples.

Images