Face feature point detection method, device and equipment based on deep knowledge migration

Abstract

The embodiment of the invention discloses a face feature point detection method, device and equipment based on deep knowledge migration, and the method comprises the steps: providing a human face dataset, and carrying out the cutting of a face image according to a face detection frame provided by the face data set or a surrounding frame of face feature points, and obtaining a training set, a verification set and a test set; inputting the test sample and the training sample into an initial face alignment network framework; training a teacher network and a student network in the initial face alignment network framework by using Pytorch, and generating a training model until the loss function and the maximum number of iterations meet a predetermined condition; freezing model parameters of the teacher network, extracting deep-layer dark knowledge learned by the teacher network, and transmitting the deep-layer dark knowledge to the student network to generate a final face alignment networkmodel; and inputting the RGB face image in the natural scene into the final face alignment network model, and outputting a face feature point detection result. The face feature point detection precision is high, and the model parameter quantity and the calculation complexity are low.

Description

technical field [0001] Embodiments of the present invention relate to the fields of computer vision and digital image processing, and in particular to a face feature point detection method, device and equipment based on deep knowledge transfer. Background technique [0002] The existing face feature point detection methods cannot effectively solve the facial feature point location in natural scenes. The complex method has a large number of model parameters and high computational complexity, which cannot meet the needs of running speed. Simple methods cannot cope with interference from factors such as extreme postures, variable lighting, and severe occlusions in natural scenes, and the accuracy cannot meet application requirements. Contents of the invention [0003] The purpose of the embodiments of the present invention is to provide a face feature point detection method, device and equipment based on deep knowledge transfer, to solve the problems of high computational com...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the embodiments of the present invention is to provide a face feature point detection method, device and equipment based on deep k

Images