Training method of network model for secondary face detection

Abstract

The invention provides a training method for a network model for secondary face detection, and the method comprises the steps: S0, carrying out the sample collection of a face detection training set through employing integrated circuit chip equipment, wherein the step S0 further comprises the following sub-steps: S01, taking each picture as an input picture, carrying out detection through integrated circuit chips, and taking results detected by all the integrated circuit chips as primary training samples of secondary detection; S02, classifying the primary training samples, taking pictures with faces as positive samples, and taking samples without faces as negative samples; and S03, manually marking an external rectangular frame of the face on the positive sample, wherein the external rectangular frame marked with the face is completely the same as the external rectangular frame of the face required by face recognition in rule; and S1, reversely calculating a gradient value by calculating the difference between a network output result and annotation information, and training the whole network;

Description

technical field [0001] The invention relates to the technical field of face image recognition, in particular to a training method of a network model for secondary face detection. Background technique [0002] With the continuous development of science and technology, especially the development of computer vision technology, face recognition technology is widely used in various fields such as information security and electronic authentication, and the image feature extraction method has good recognition performance. Face recognition refers to the technology of identifying one or more faces from static or dynamic scenes by using image processing and / or pattern recognition technology based on the known face sample library. But the current face recognition technology includes 1. Face detection of traditional machine learning. 2. Face detection based on deep learning. 3. It is used for front-end face detection. Its disadvantages include: there are certain false detections in t...

AI Technical Summary

Problems solved by technology

Its disadvantages include: there are certain false detections in the front-end face detection, the detected face frame and the judgment standard of whether it is a face do not match the requirements of face recognition, resulting in a decline in the recognition rate of face recognition or even failure to use normally

Images