Face key point detection method and device based on deep reinforcement learning

Abstract

The invention discloses a face key point detection method and device based on deep reinforcement learning, wherein the method comprises the following steps: mathematically modeling a face key point detection problem by a Markov decision process; obtaining an initial shape by a shape prediction network, subjecting the initial shape to the k-nearest neighbor to obtain a shape candidate subset; evaluating each candidate shape in the shape candidate subset by the shape decision network, and obtaining the shape with the highest score; simultaneously optimizing the shape prediction network and the shape decision network by a strategy gradient to obtain the final predicted decision network structure to obtain the key points of a face. By predicting the framework of decision, the method can find an optimal shape search path in the shape continuous space to maximize the shape evaluation score, thereby effectively improving the accuracy and reliability of face key point detection.

Description

technical field [0001] The present invention relates to the technical field of computer vision, in particular to a method and device for detecting human face key points based on deep reinforcement learning. Background technique [0002] Face key point detection aims at locating the positions of multiple feature key points (such as eyebrows, eyes, nose, mouth, face profile, etc.) for a given face image. This technology plays an important role in multiple face analysis characters, such as face recognition, head pose estimation, face attribute analysis, etc. [0003] Although a series of methods have been devoted to the research of face key point detection in recent years, the problem of face key point detection is still very challenging. This is mainly due to the fact that the face images obtained in natural open scenes have great variability due to large postures and large expressions, which makes the algorithm of face key point detection easy to fall into local optimum, and...

AI Technical Summary

Problems solved by technology

This cascading approach leads to the accumulation of errors between different stages, which eventually leads to skewed results

Images