Human face attribute recognition method and device

Abstract

The embodiment of the invention discloses a human face attribute recognition method and device, and the method comprises the steps: generating a human face attribute image data set comprising human face attribute tags; constructing a human face attribute recognition network model based on multiple tasks, and training the human face attribute recognition network model by taking the human face attribute image data set as a training sample to obtain a first human face attribute recognition network model; testing the first human face attribute recognition network model based on multiple tasks, andadjusting configuration parameters of the first human face attribute recognition network model according to a test result to obtain a second human face attribute recognition network model; and embedding the second human face attribute recognition network model, performing human face attribute recognition on the acquired human face data, and outputting a recognition result based on the constructeddisplay interface. By adopting the method provided by the invention, a plurality of face attributes can be simultaneously identified by utilizing the single network model, the identification precision is improved by utilizing the potential association relationship among the attributes, and the computing resources are saved.

Description

technical field [0001] Embodiments of the present invention relate to the field of computer vision, and in particular to a method and device for identifying human face attributes. In addition, it also relates to an electronic device and a storage medium. Background technique [0002] In recent years, with the continuous development of the Internet information age, face recognition technology with big data and artificial intelligence technology as the core has begun to be widely used in daily life. In particular, deep learning technology is constantly attracting people's attention because of its good ability to describe complex objects, and it is gradually being applied in various aspects in the industry. Convolutional Neural Network (CNN) is a deep feed-forward artificial neural network, because the convolutional neural network avoids the complex pre-processing of images, and thus has been widely used in the field of image recognition. Computer vision is the first field to...

AI Technical Summary

Problems solved by technology

[0004] For this reason, the embodiment of the present invention provides a face attribute recognition method to solve the face attribute recognition scheme existing in the prior art, which is difficult to calculate, consumes a lot of resources, and multiple tasks are usually relatively independent, so it is impossible to improve the model. The problem of generalization ability

Images