Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Face detection method and device

A face detection and detection model technology, applied in the field of image processing, can solve the problem of low detection accuracy of small-scale faces, achieve high feature resolution, and improve detection accuracy.

Pending Publication Date: 2019-05-14
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the detection accuracy for small-scale faces in images is still not high, for example figure 1 In the image shown, traditional methods are difficult to detect figure 1 Small-scale human faces in the middle stand

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

Embodiment Construction

[0056] Embodiments of the present application are described below in conjunction with the accompanying drawings.

[0057] The inventors of the present invention found in the research that in the traditional face detection method, the features of the candidate area of ​​the face can be extracted by using a multi-layer convolutional network, and face recognition can be performed based on the features output by the last layer of the convolutional network . Since the multi-layer convolutional network is used to extract the features of the face candidate area, the method of layer-by-layer extraction is generally adopted, and the latter layer of convolutional network continues to extract based on the features output by the previous layer of convolutional network to obtain more characteristics of semantic information. The latter layer of convolutional network continues the process of extracting features from the features output by the previous layer of convolutional network, which i...

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 discloses a face detection method and device. The method comprises: determining a human face candidate area in the to-be-detected image according to a human face detection model comprising a multi-layer convolutional network, determining that the face candidate area is a corresponding small-scale face according to the size parameters of the face candidate area; facedetection is carried out on the face candidate area through a first detection model; performing face detection on a face candidate region; obtaining projection characteristics of the face candidate area on a characteristic pattern output by at least two layers of convolutional networks in the face detection model, fusing the projection feature of the first convolutional network and the projectionfeature of the second network to obtain a fusion feature. Compared with the prior art, the method has the advantages that the feature resolution ratio is high, more semantic information is carried, the small-scale face can be detected easily, and therefore when the fusion feature serves as the projection feature of the first convolutional network and face detection is conducted on the face candidate area according to the projection features of at least two layers of convolutional networks, the detection precision of the small-scale face can be improved.

Description

technical field [0001] The present application relates to the field of image processing, in particular to a face detection method and device. Background technique [0002] Face detection is an important research hotspot in the field of computer vision. Its main task is to detect the faces in the image from the image. [0003] At present, there are many traditional face detection methods, which improve the accuracy and speed of face detection from different angles. However, the detection accuracy for small-scale faces in images is still not high, for example figure 1 In the image shown, traditional methods are difficult to detect figure 1 Small-scale faces in the middle stand. [0004] It can be seen that in face detection, the detection of small-scale faces in images is an urgent problem to be solved. Contents of the invention [0005] In order to solve the above technical problems, the present application provides a face detection method and device. [0006] The embo...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06N3/04G06V10/25
CPCG06V40/161G06V10/25G06V10/454G06V10/82G06N3/045G06F18/24143G06N3/08G06F18/25G06F18/285
Inventor 武文琦叶泽雄肖万鹏
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products