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

Method and device for selecting image of human face

An image and face technology, applied in the field of face image selection method and device, can solve the problems of high cache occupancy, time extension, slow processing speed, etc., to improve processing speed, reduce delay, and reduce cache occupancy amount of effect

Active Publication Date: 2018-12-18
ZHEJIANG DAHUA TECH CO LTD
View PDF7 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a face image selection method and device, which are used to solve the problems of slow processing speed, long time delay, and high cache occupation in the prior art when selecting a face image

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
  • Method and device for selecting image of human face
  • Method and device for selecting image of human face
  • Method and device for selecting image of human face

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] figure 1 A schematic diagram of a human face image selection process provided by an embodiment of the present invention, the process includes:

[0048] S101: Acquire a first image of each human face existing in a current image frame of a video stream, and determine a first quality score representing the quality of each human face in the first image.

[0049] The face image selection method provided by the embodiment of the present invention is applied to an electronic device, and the electronic device may be an image acquisition device, such as a video camera, a camera, etc., or may be a mobile phone, a personal computer (PC), a tablet computer, and the like.

[0050] Specifically, electronically obtain the current image frame of the video stream, and detect the current image through face detection algorithms, such as face detection algorithms based on histogram rough segmentation and singular value features, face detection algorithms based on binary wavelet transform, ...

Embodiment 2

[0061] In order to ensure the accuracy of face image selection, on the basis of the above embodiments, in the embodiment of the present invention, if the first image of the face corresponding to the saved second image is not obtained in the current image frame, the Methods also include:

[0062] Outputting the second image as a target image.

[0063] Specifically, if the first image of the human face corresponding to the saved second image is not obtained in the current image frame, it is determined that the human face corresponding to the second image has disappeared from the video stream, and the stored image of the human face of the electronic device The face quality of the second image of the human face is the best, and the electronic device outputs the second image of the human face as the target image.

[0064] In addition, in order to further improve the accuracy of image selection of the human face, if the acquisition sequence of the second image of the human face is ...

Embodiment 3

[0069] In order to ensure the efficiency and accuracy of face image selection, on the basis of the above embodiments, in the embodiment of the present invention, the first image of the face and the saved second image of the face are selected The image with a higher quality score is re-saved as the second image of the face, and the image frame of the image with a higher quality score is obtained, in the order of the image frames of the image of the face obtained, The acquisition sequence re-save as the second image of the face includes:

[0070] Judging whether the first quality score of the first image of the human face is greater than the second quality score of the second image of the human face stored;

[0071] If so, update the second image of the saved face with the first image of the face as the second image, and obtain the image of the face according to the image frame of the first image of the face The order in the image frame of the human face is updated to update th...

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 discloses an image selection method and a device of a human face. The method comprises the following steps: acquiring a first image of each human face existing in a current image frame of a video stream, and determining a first quality score representing the face quality of each first image; obtaining a first image of each human face existing in the current image frame of the video stream; and determining a first quality score representing the face quality of each first image; for a face corresponding to each of the first images acquired from the current image frame, selecting animage having a higher quality score from the first image of the face and the saved second image of the face, a second image as the face being restored, and an image frame of an image having a high quality score being restored as an acquisition order of a second image of the face in an order of image frames in which the image of the face is acquired; and outputting the second image of the face asa target image when the total number of times of acquiring the image of the face is greater than the threshold value of the corresponding number of times of the face and the acquisition order of the second image of the face is less than the threshold value of the corresponding order of the face. A fast and efficient face image selection scheme is provided.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a face image selection method and device. Background technique [0002] With the rapid development of the economy and the continuous innovation of science and technology, face recognition technology has been widely used in access control systems, bayonet systems, information collection systems, etc., bringing great convenience to people's production and life. However, in the process of face recognition, due to the quality of the face image, it is easy to fail to recognize or have errors in recognition. Therefore, how to choose a high-quality face image for face recognition has become an important issue. The problem. [0003] In the prior art, when selecting a human face image, the definition of the human face is usually used as the selection index, and for each human face appearing in the image frame of the video stream, the face that appears in the image frame of the v...

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): G06T7/00G06K9/00
CPCG06T7/0002G06T2207/30168G06V40/161G06T2207/30201G06V40/172G06V40/50G06V10/993G06V40/173G06V40/166G06V40/169
Inventor 陈广刘星
Owner ZHEJIANG DAHUA TECH CO LTD