Human face emotion recognition method in complex environment

Abstract

The invention discloses a human face emotion recognition method in a mobile embedded complex environment. In the method, a human face is divided into main areas of a forehead, eyebrows and eyes, cheeks, a noise, a month and a chain, and 68 feature points are further divided. In view of the above feature points, in order to realize the human face emotion recognition rate, the accuracy and the reliability in various environments, a human face and expression feature classification method is used in a normal condition, a Faster R-CNN face area convolution neural network-based method is used in conditions of light, reflection and shadow, a method of combining a Bayes Network, a Markoff chain and variational reasoning is used in complex conditions of motion, jitter, shaking, and movement, and a method of combining a deep convolution neural network, a super-resolution generative adversarial network (SRGANs), reinforcement learning, a backpropagation algorithm and a dropout algorithm is used in conditions of incomplete human face display, a multi-human face environment and noisy background. Thus, the human face expression recognition effects, the accuracy and the reliability can be promoted effectively.

Description

technical field

[0001] The invention relates to the technical field of artificial intelligence mobile video image recognition, in particular to a face recognition method in a complex environment, which is an emerging field in the world at present. Background technique

[0002] Face recognition based on video images is an emerging important research field in the world. Since NVIDIA launched the deep learning graphics processor graphics card (GPU) based on servers and computer hosts in 2006, the world's leading high-tech companies Such as Google, Apple, Amazon, well-known scientific research institutes such as MIT, Berkeley and Stanford, have adopted Nvidia's GPU graphics card to develop image recognition-based applications. In contrast, the global mobile embedded video image recognition market lags far behind similar server-based applications. It was not until mid-May 2017 that manufacturers including Nvidia began to provide high-performance machine vision and deep learning G...

Images