Deep convolutional neural network-based human face occlusion detection method

Abstract

The invention discloses a deep convolutional neural network-based human face occlusion detection method. The method comprises the steps of performing block segmentation on an input image to obtain a target pre-selected region; constructing a first deep convolutional neural network, training the first deep convolutional neural network comprising a first deep convolutional network and a first multilayer perceptron connected with the first deep convolutional neural network to obtain required parameters, extracting features of the target pre-selected region, and performing classification; predicting the position of a human head through a second multilayer perceptron according to the extracted features; filtering the credibility of a classification type which is the human head and the predicted position of the human head through non-maximum suppression to remove an overlapped duplicate detection box; and obtaining a human head block in combination with original image segmentation, constructing a multi-task learning policy-based second deep convolutional neural network, and judging whether the left eye, the right eye, the nose and the mouth of the human head block are occluded or not. According to the method, the occluded human face can be accurately detected and the specific occluded part of the human face can be judged; and the method is mainly used for crime pre-warning of videos of a camera in front of an automatic teller machine.

Description

technical field [0001] The present invention relates to a face occlusion detection method, in particular to a face occlusion detection method based on a deep convolutional neural network. Background technique [0002] Automatic Teller Machines (ATMs) have been a target of criminals since their widespread introduction in the 1970s. For example, scammers use various means to obtain user card numbers and passwords. Real-time automatic alarm system is the most direct technology to solve this problem. Because surveillance cameras are installed on almost all ATMs. However, the video needs to be supervised by humans 24 hours a day, but human fatigue and distraction will be inevitable. Therefore, politicians and businessmen urgently need a face occlusion detection method for ATMs. [0003] Face occlusion detection has been studied for several years, and several methods have been proposed, many of which are aimed at enhancing the security of ATMs. However, its feature expression...

AI Technical Summary

Problems solved by technology

[0004] Recently, the most successful method of object detection is to use the well-known sliding window (sliding window) mode. However, in order to accurately detect objects with large size changes, this method will lead to a sharp increase in the calculation of subsequent classifiers.

Images