Human face detection method and device

Abstract

The invention provides a human face detection method and device, which belongs to the technical field of image recognition. The method comprises the steps that the position response feature map of a human face correction candidate area in an original image is acquired; the position response feature map is divided to acquire the corresponding number of squares, and the square type of all squares is distinguished according to the position of each square; the weight corresponding to each square type is determined according to the human face detection contribution degree corresponding to each square type; the area feature vector corresponding to the human face correction candidate area is calculated based on the feature vector and weight corresponding to each square; and based on the area feature vector, an area containing a human face in the original image is output. The influence of external conditions on detection results in complex scenes can be reduced by introducing the weights of different human face parts for different square types in the position response feature map. The accuracy of human face detection is high, and the applicability of human face detection is improved.

Description

technical field [0001] The present invention relates to the technical field of image recognition, and more specifically, to a face detection method and device. Background technique [0002] In recent years, face detection technology has been widely used in many fields such as identification, account registration, financial payment and security prevention and control. Face detection technology, which detects the position of a face in a picture or a video. Existing face detection methods are mainly based on Haar features and Adaboost classifiers for face detection, that is, first determine the face candidate areas in the original image, calculate several rectangular features in the face candidate areas, and train out the corresponding rectangular features. The weak classifier corresponding to the feature. Then, let each candidate area pass through the weak classifier step by step, if the confidence is lower than the threshold, no further judgment will be made and the candida...

AI Technical Summary

Problems solved by technology

[0003] In the process of realizing the present invention, it is found that the prior art has at least the following problems: because the Haar feature characterization ability is weak, and the application scene of face detection tends to be complex and changeable gradually, the face detection process based on Haar feature cannot Meet the application requirements of complex scenarios, so the accuracy of face detection is low in complex application scenarios

Images