A Tiny Face Recognition Method Based on Generative Adversarial Network

Abstract

The invention provides a tiny face recognition method based on generating confrontation network. The present invention is proposed in order to solve the shortcoming that the current face detection technology cannot capture tiny faces in complex backgrounds, and the detection rate will seriously drop when performing face detection based on distorted images, including: using an existing The face detector predicts the face position of each picture in the training database, and intercepts and saves the real face and non-face images; according to the down-sampling of face images and non-face images, the corresponding low-resolution images are obtained; construction Generate a confrontation network, the generation confrontation network includes a generator and a discriminator; use high-resolution face, non-face images and corresponding low-resolution face, non-face images to train the generation confrontation network; according to the discriminator from The scores of face candidate regions obtained by existing face detectors mark the positions of faces in the input image. The invention is applicable to the recognition and detection of human faces.

Description

technical field [0001] The present invention relates to the field of face recognition, in particular to a small face recognition method based on a generative confrontation network. Background technique [0002] Face detection is a very important basic research topic in the field of machine vision. It is the basic technology for advanced tasks such as face parsing, face verification, and face tagging. In addition, face recognition is playing an increasingly important role in the fields of friend recommendation, automatic tagging of photo albums, security and anti-terrorism. It also provides a good solution for modern identification and has a wide range of application prospects. [0003] Due to the important theoretical research value and urgent practical application requirements of face detection technology, the corresponding technology for face detection is also constantly developing and updating, which can be roughly divided into two categories: traditional methods of face...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the problem that the deep learning technology at the present stage does not have the ability to capture tiny faces in complex backgrounds, and when face detection is performed based on distorted images, the detection rate will seriously drop, and a method based on generative confrontation is proposed. Tiny face recognition methods for the web, including:

Images