Face detection method and apparatus, and terminal equipment

Abstract

Embodiments of the invention disclose a face detection method and apparatus, and terminal equipment, and are applied to the technical field of information processing. The face detection apparatus performs feature sampling according to feature information of an image in a face candidate frame of a to-be-processed picture and obtains a plurality of pieces of sampling feature information, then a detection score is obtained according to a preset calculation function and the plurality of pieces of sampling feature information, and finally, the image in the face candidate frame is classified according to the detection score, namely, a classification result whether the image in the face candidate frame is a face can be obtained. Therefore, the plurality of pieces of sampling feature information can be obtained through feature sampling, features of the image in the face candidate frame are selectively expressed, and the finally obtained classification result is accurate; and the detection score of the image in the face candidate frame is obtained through the plurality of pieces of sampling feature information, and the plurality of pieces of sampling feature information obtained through anyfeature sampling mode can have the same detection scores so that the precision of the finally obtained classification result is improved.

Description

technical field [0001] The present invention relates to the technical field of information processing, in particular to a face detection method, device and terminal equipment. Background technique [0002] Face detection has always been an important research topic in the field of computer vision, and it is also the basis for applications such as face recognition, face alignment and face tracking. Existing face detection methods generally adopt neural network-based schemes, which can generally be divided into three categories: cascade-based methods, single-stage-based methods, and two-stage-based methods. [0003] Among them, the detection accuracy is the highest based on the two-stage method, such as the Regional Fully Convolution Network (RFCN) method. Specifically, the two-stage method generally uses the strategy of object-likeness detection to generate a series of Potential face candidate frames, and then use the convolutional neural network to extract the corresponding ...

AI Technical Summary

Problems solved by technology

[0004] However, the existing two-stage method is a technical solution for general target detection, and there is no targeted measure for a specific target object. Since the target in a general scene often has a small change scale, this method is based on the existing two-stage method. The detection result obtained after selecting the face candidate frame by the method is more accurate

In some cases, for example, when the detection target is a human face, due to the many changes in the orientation, zoom scale and expression of the human face, the detection results obtained by the existing two-stage method for face detection are not very accurate.

Images