Face detection acceleration method and system, computer equipment and storage medium

Abstract

The invention relates to a face detection acceleration method and device, computer equipment and a storage medium. The method comprises the following steps of acquiring a face image, setting a minimumdetection face pixel, and determining a zooming factor according to the minimum detection face pixel, zooming the face image for multiple times according to the zooming factor to obtain a plurality of detection images in a picture pyramid shape, splicing the remaining detection images except the detection image with the largest area in the detection images to generate a spliced image, and sendingthe detection image with the largest area in the detection images and a spliced image generated by splicing a plurality of detection images into a PNET network as two input images for detection. Theimage obtained by splicing the image zoomed for the first time and the image zoomed for the remaining time is input into the MTCNN model in turn for only two times of detection, which is far less thanthe original 7-11 times of detection, so that the acceleration effect is achieved.

Description

technical field [0001] The present application relates to the technical field of face recognition, in particular to a face detection acceleration method, system, computer equipment and storage medium. Background technique [0002] Face detection refers to searching for any given image with a certain strategy to confirm whether there is a face in the image, and if so, return the size and position information of the face in the image. The current face recognition system that is widely used in people's daily life: face payment in daily transactions, face recognition used in station security checks and other technologies are all based on the detection of faces before subsequent liveness detection and detection. Face recognition detection. Therefore, face detection technology is not only the basis of face recognition, but also one of the key links of face recognition. [0003] The existing face detection technology usually uses deep learning technology to train the model to aut...

AI Technical Summary

Problems solved by technology

[0003] The existing face detection technology usually uses deep learning technology to train the model to automatically identify the position of the face in the image, and most of these models have too many model parameters, or the detection process is too complicated although the model parameters are few For example, in order to detect faces of different sizes, the image is scaled and cyclically input into the model, causing the model to perform repeated detection

It takes a long time to make the model on edge devices (such as door locks, smart cameras, mobile phones), the user experience is poor, and it cannot run in a real-time detection environment

Images