Multi-scale fast human face detection method for convolutional neural network feature fusion

Abstract

The invention discloses a multi-scale fast human face detection method for convolutional neural network feature fusion. The method comprises the following steps: step 1, based on a model structure ofan SSD fast target detection method, a feature extraction method in the SSD is transformed, a feature fusion method is added, and a modified detection model is obtained; step 2, human face detection training is carried out on the detection model transformed in the step 1, and a trained deep neural network model is obtained; step 3, the to-be-detected picture is calculated by using a deep neural network model trained in the step 2, to obtain a model output result. According to the invention, the human face in the image can be quickly recognized and the human face can be accurately positioned, so that the human face is separated from the complex background, and a foundation is provided for identity verification and tracking of people in an image.

Description

technical field [0001] The invention belongs to the technical field of computer digital image processing and pattern recognition, and in particular relates to a face detection method. Background technique [0002] With the increase in the number of surveillance cameras in our country, massive amounts of surveillance video data are generated every day. In this context, computer-aided surveillance video content analysis technology becomes necessary and urgent. In surveillance video, the objects we monitor are mainly people, and facial features are the most important information for us to use image information for identification and verification. Face detection can locate the position of all faces in the picture and separate the face from the background, which is the premise of subsequent face representation and face recognition. Therefore, face detection is the first step in surveillance video content analysis. [0003] The current methods of target detection mainly include...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a multi-scale fast face detection method with deep feature fusion, which can locate the positions of all faces in the picture, so as to overcome the high miss detection rate and false detection rate of the SSD fast target detection method, And the accuracy of the detection frame positioning is poor.

Images