Scale estimation-based human face detection method

Abstract

The invention discloses a scale estimation-based human face detection method. According to the method disclosed in the invention, a size of a human face on an image is estimated via human face scale estimation, the image is zoomed based on a human face scale, a suggestion frame extraction is performed rapidly via a full convolution network, and a human face detection result can be obtained via twotimes of cascaded classification and regression. According to the method, human face detection is performed based on combination of human face scale estimation and a cascaded convolution neural network, an overall calculation amount of human face detection can be reduced, overall time consumption for human face detection can be reduced, and human face detection effects can be ensured.

Description

technical field [0001] The invention belongs to the technical field of video monitoring and relates to a face detection method based on scale estimation. Background technique [0002] The function of the face detection method is to judge whether there is a face in the picture or video, and if there is a face, predict the position and size of the face. Face detection is the basis for various analysis of human faces. The time-consuming of face detection is one of its key problems. In most cases, in order to reduce time consumption, part of the detection effect has to be sacrificed. The scale estimation of the face can greatly reduce the time-consuming of face detection. [0003] Among the existing technologies, "A Method and Device for Face Detection-201510639824.8" uses the AdaBoost method to classify on the basis of fast multi-scale pyramid feature data extraction, which can effectively reduce the computational cost while ensuring the detection accuracy. However, the Ada...

AI Technical Summary

Problems solved by technology

[0003] Among the existing technologies, "A Method and Device for Face Detection-201510639824.8" uses the AdaBoost method to classify on the basis of fast multi-scale pyramid feature data extraction, which can effectively reduce the computational cost while ensuring the detection accuracy. amount, but the AdaBoost method cannot effectively use the current large amount of training data to improve the detection performance

"Method and Device for Face Detection-201610206093.2" uses AdaBoost to extract suggestion frames and then uses convolutional neural network for face detection. The threshold selection of the suggestion frame extraction in the first step of this method needs to be adjusted in different scenarios, which is cumbersome

"Method and Device for Face Detection-201710618497.7" uses a cascaded convolutional neural network for face detection, because the overall calculation is large and the time-consuming problem is serious

Images