Face detection method and device

Abstract

The embodiment of the invention discloses a face detection method and device. The concrete embodiment of the method comprises the steps that an image to be detected is acquired; the image to be detected is inputted to a first convolutional neural network trained in advance so as to obtain face feature information and body feature information, wherein the first convolutional neural network is usedfor extracting face features and body features; and the face feature information and the body feature information are inputted to a second convolutional neural network trained in advance so as to obtain the face detection result, wherein the second convolutional neural network is used for representing the corresponding relation of the face feature information, the body feature information and theface detection result. According to the method, the accuracy of the detection result under the condition of small face scale can be enhanced.

Description

technical field [0001] The present application relates to the field of computer technology, specifically to the field of Internet technology, and in particular to a face detection method and device. Background technique [0002] With the development of Internet technology, face detection technology has been applied to more and more fields. For example, identity verification and the like can be performed through face detection. Existing face detection methods usually detect face regions directly from images. However, when the scale of the face area in the image is small (such as monitoring images of train stations, hotels, etc.), usually the face is only displayed as a small flesh-colored area, and details such as facial features cannot be presented, resulting in the failure to successfully detect the face. , the existing methods have the problem of low accuracy of detection results when the face scale is small. Contents of the invention [0003] The purpose of the embod...

AI Technical Summary

Problems solved by technology

However, when the scale of the face area in the image is small (such as monitoring images of train stations, hotels, etc.), usually the face is only displayed as a small flesh-colored area, and details such as facial features cannot be presented, resulting in the failure to successfully detect the face. , the existing method has the problem of low accuracy of detection results when the face scale is small

Images