Improved face key point detection method based on GIOU and weighted NMS

Abstract

The invention relates to an improved face key point detection method based on GIOU and weighted NMS. Firstly, a lightweight cascaded face target detection network is adopted to carry out detection androtation angle detection on a face target in an image, GIOU is adopted to replace IOU to serve as a target frame position precision index, and IOU loss is adopted to carry out position regression; secondly, a weighted NMS suppression method is adopted for the obtained face target, and a face target box with high confidence in the image is obtained; and finally, the face key points are detected and regressed by adopting a lightweight cascaded face key point detection network. Compared with a traditional convolutional network, the speed is improved, the real-time performance of the algorithm isenhanced, and the network detection precision is improved on the premise of not additionally increasing the operand. The problem that a traditional target detection and face key point detection method is poor in real-time performance is solved, and real-time key point detection can be carried out on face targets in multiple different rotating directions in a complex environment under the condition that the detection precision is guaranteed.

Description

technical field [0001] The invention belongs to the technical field of computer digital image recognition, and relates to an improved human face key point detection method based on GIoU (Generalized Intersection over Union) and weighted NMS (Convolutional Neural Network), which realizes multi-face target detection and human face detection in a complex environment in one step. Key point detection, which can detect key points of multi-face targets in complex scenes in real time. Background technique [0002] With the continuous advancement of artificial intelligence and computer vision technology, biometric identification technology has gradually entered people's lives. Biometric identification refers to the use of specific biosensor devices to analyze people's inherent physiological and behavioral characteristics, and further model the data to achieve personal identity authentication. The most common biometric technologies include: fingerprint recognition, face recognition, ...

AI Technical Summary

Problems solved by technology

The traditional face key point detection method is only aimed at the key point detection and recognition of a single face image, resulting in the application of multiple face targets in a complex environment cannot be directly applied. If this task is used as a target detection and face key The two subtasks of point detection are processed, and there is a problem that it takes too long

Images