Face detection method and device

A technology of face detection and detection frame, which is applied in the direction of instruments, character and pattern recognition, computer components, etc. Performance improvement, accurate classification and prediction

Inactive Publication Date: 2018-04-03
BEIJING EYECOOL TECH CO LTD
View PDF3 Cites 67 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a face detection method to solve the problem that the detectio

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
  • Face detection method and device
  • Face detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0042] Example one

[0043] Reference figure 1 , A flowchart of a face detection method provided by an embodiment of the present invention is given.

[0044] Step 101: Use the pre-trained first convolutional neural network model to classify the image to be tested, determine the first face confidence of each input area in the image to be tested, and obtain the confidence of the first face according to the first face confidence. At least one candidate area is selected from the input area.

[0045] Among them, the first convolutional neural network includes m-layer convolutional layers.

[0046] Specifically, the first convolutional neural network is a deep convolutional neural network with deep learning capabilities, including one or more convolutional layers and pooling layers, which can realize deep learning. Compared with other deep learning structures, deep convolution Neural networks show more outstanding performance in image recognition.

[0047] Before detecting the face, you can...

Example Embodiment

[0057] Example two

[0058] Reference figure 2 On the basis of the foregoing embodiment, this embodiment further discusses the face detection method.

[0059] In an optional embodiment, before performing face detection on the image, it further includes training the first convolutional neural network model and the second convolutional neural network model.

[0060] The following are Figure 2 to Figure 4 The embodiment discusses the training process of the first convolutional neural network model and the second convolutional neural network model.

[0061] Reference figure 2 , A flowchart of training the first convolutional neural network model in a face detection method provided by an embodiment of the present invention is given:

[0062] In step 201, a face data set containing face annotations is selected as a training sample, and training images in the training sample are clipped.

[0063] Optionally, use the WIDER FACE data set as the training sample, where the WIDER FACE data set co...

Example Embodiment

[0125] Example three

[0126] On the basis of the foregoing embodiment, this embodiment also provides a face detection device, which is applied to an artificial intelligence terminal.

[0127] Reference Figure 13 A structural block diagram of a face detection apparatus provided by an embodiment of the present invention is given, which may specifically include the following modules:

[0128] The pre-classification module 1301 is configured to use the pre-trained first convolutional neural network model to classify the image to be tested, to determine the first face confidence of each input area in the image to be tested, and to determine the first face confidence level according to the first face The confidence level screens out at least one candidate region from the input region, and the first convolutional neural network includes m-layer convolutional layers.

[0129] The secondary classification module 1302 is configured to use a pre-trained second convolutional neural network mode...

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 embodiment of the invention provides a face detection method and device, and the method comprises the steps: employing a pre-trained first convolution neural network model for the classification of a to-be-detected image, screening out at least one candidate region from a to-be-detected image input region, employing a pre-trained second convolution neural network model for the classification of the candidate regions, screening out at least one selected region from the candidate regions, carrying out the removing and clustering of detection frames according to at least one selected region,so as to obtain a human face detection region. Because the input region of the first convolution neural network is very small, the calculation speed of human face detection is improved. In addition, because the two convolution neural network models at different depths are employed, the secondary classification of the obtained candidate regions is carried out, and the classification prediction is enabled to be more accurate. Meanwhile, a large number of false detection samples are filtered out, and the detection performances are improved.

Description

technical field [0001] Embodiments of the present invention relate to the field of artificial intelligence, and in particular to a face detection method and device. Background technique [0002] Face detection refers to the process of determining the location and size of all faces from an input area. As a key technology in face information processing, face detection is the premise and foundation of many automatic face image analysis applications, such as face recognition, face registration, face tracking, face attribute recognition, etc. The first step in the human-computer interaction system. Not only that, most of the current digital cameras are embedded with face detection technology to automatically focus, and many social networks such as FaceBook use face detection technology to achieve image annotation. [0003] With the development of artificial intelligence, face detection methods have also been developed to a certain extent, but there are still some deficiencies. ...

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): G06K9/62G06K9/00
CPCG06V40/161G06V40/172G06F18/214G06F18/24
Inventor 段旭宋丽张祥德
Owner BEIJING EYECOOL TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap