Face detection model training method and device, electronic device and storage medium

Abstract

The invention relates to a face detection model training method and device, an electronic device and a storage medium, and relates to the technical field of image processing. The method and the deviceare used for solving the problem of poor detection effect of a face detection model on a small-scale face in the related art, and the method comprises the steps: determining a positive sample pixel range detected by each feature layer according to an anchor point corresponding to each feature layer in the face detection model; determining a target training image corresponding to each feature layer from the training images of the face detection data set according to the proportion of the number of the negative samples between the feature layers, the target training image corresponding to the feature layer being a training image of which the face scale being within a positive sample pixel range detected by the feature layer; using the target training images corresponding to the feature layers to train the face detection model, and determining the target training images corresponding to the feature layers based on the proportion of the number of the negative samples so that the detectioneffect of the small-scale face can be enhanced.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, and in particular to a training method, device, electronic equipment and storage medium for a face detection model. Background technique [0002] Face detection is the first step in all face-related tasks. After the face is detected, face recognition, face attribute analysis, and face key point extraction can be performed. Its main task is to judge whether there is a human face on a given face image, and if there is a human face, give the position and size of the human face. Compared with general-purpose objects, the scale of human faces varies greatly. For a 640x640 picture, the pixel size of human faces varies from 10 to 640. [0003] In the field of face detection, the detection of small-scale faces is a difficult problem. The learning of small-scale face detectors requires a large amount of small-scale face data, but at the same time it cannot reduce the performance of ordi...

AI Technical Summary

Problems solved by technology

[0004] The present disclosure provides a face detection model training method, device, electronic equipment, and storage medium to at least solve the problem that the face detection model in the related art has a poor detection effect on small-scale faces

Images