Unlock instant, AI-driven research and patent intelligence for your innovation.

Face detection method and device and equipment and computer readable storage medium

A face detection and detection algorithm technology, applied in the field of face recognition, can solve problems such as difficult to solve real-time problems, and achieve the effects of improving detection speed and accuracy, small memory footprint, and high real-time performance

Pending Publication Date: 2020-05-15
CHINA PING AN LIFE INSURANCE CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These improved Hough transforms are difficult to solve real-time problems when the noise interference is relatively large

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Face detection method and device and equipment and computer readable storage medium
  • Face detection method and device and equipment and computer readable storage medium
  • Face detection method and device and equipment and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] refer to figure 1 As shown, it is a schematic flowchart of a face detection method provided by an embodiment of the present invention. The method may be performed by a device, and the device may be implemented by software and / or hardware.

[0051] In this embodiment, the face detection method includes:

[0052] Step S1: Collect sample images of human head pictures in real time, and train the sample images based on the target object detection algorithm yolov3 to obtain a trained human head detection network model;

[0053]Specifically include the following steps:

[0054] 1) Create sample sets and label files

[0055] 1.1) Sample collection: Preprocess the collected sample images and make a pedestrian sample set;

[0056] 1.2) Convert the size of the collected sample image to 2048×2048, and randomly divide the sample set formed by the sample image into a training set and a verification set according to a certain ratio;

[0057] 1.3) Obtain the head labeling informat...

Embodiment 2

[0092] This embodiment is basically the same as the first embodiment, a face detection method, characterized in that the method comprises the following steps:

[0093] Step S1: Real-time head detection based on the target object detection algorithm YOLOv3 to obtain a head picture;

[0094] Step S2: Use the trained YOLOv3 network model to detect the head, obtain the head bounding box information, and intercept the bounding box where the head is located on the head picture through the head bounding box information to obtain a sub-image;

[0095] Step S3: performing skin color clustering on the sub-images, and extracting head features;

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a face detection method, apparatus and device, and a computer readable storage medium. The face detection method comprises the steps of performing real-time collection to obtaina sample image; training the sample image based on a target object detection algorithm to obtain a human head detection network model; inputting a to-be-detected target image into the human head detection network model to obtain human head bounding box information, and intercepting a sub-image containing a human head from the target image according to the human head bounding box information; andperforming skin color clustering on the sub-images, and calculating the skin proportion of the sub-images to realize human head detection. The human face detection method is used for real-time human head detection based on the target object detection algorithm, the detected human head picture is used for obtaining the skin proportion area based on the skin color clustering model to judge whether the human face is a human face or a non-human face, the human face detection method can be used for both a human head counting scene and a human face recognition scene, and the detection speed and precision can be improved.

Description

technical field [0001] The present invention relates to the technical field of face recognition, in particular to a face detection method, device, equipment and computer-readable storage medium. Background technique [0002] The detection of human activities has played a key role in many applications such as automatic video surveillance and human-computer interaction. In the computer-implemented automatic identification system, the detection of the human head is considered to be one of the most effective means of detecting human activities. Nowadays, head detection has been applied in many fields, such as the detection of pedestrians and the detection of passenger flow. For the detection of passenger flow, cameras are usually installed above people's heads and shoot from top to bottom. The main task of head detection is to determine the size and position of the head part. The real-time image collected by the camera is used as input, the automatic recognition system proces...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06K9/34G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V40/166G06V40/168G06V10/267G06V10/56G06N3/045G06F18/23
Inventor 熊军
Owner CHINA PING AN LIFE INSURANCE CO LTD