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

Character age determination method and device, equipment and storage medium

A technology for determining methods and characters, applied in the field of image recognition, can solve problems such as the need to improve the prediction accuracy, achieve the effect of improving recommendation accuracy and ensuring effective recognition

Pending Publication Date: 2020-05-12
GUANGZHOU BAIGUOYUAN NETWORK TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the age recognition technology of people is mainly based on deep learning and uses face features combined with face recognition and other algorithms to predict the age of people. However, this type of technology usually only outputs the predicted age of each person for a single image or a single video frame, and the prediction is accurate. Degree to be improved

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
  • Character age determination method and device, equipment and storage medium
  • Character age determination method and device, equipment and storage medium
  • Character age determination method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] figure 1 A schematic flow chart of a method for determining a character's age provided by Embodiment 1 of the present invention is given. This method is applicable to the situation of determining the age group of a character in a video. The method can be executed by a device for determining the age of a character, wherein , the device can be realized by software and / or hardware, and can generally be integrated on computer equipment.

[0028] It should be noted that in this embodiment, the executor of the provided method can be regarded as a background server that provides background service support for multimedia function application software (including live broadcast application software, etc.), and the obtained video can be processed by the executor. Analysis to determine the age attribution of the characters in the video.

[0029] Such as figure 1 As shown, the method for determining the age of a person provided in Embodiment 1 of the present invention specifically...

Embodiment 2

[0044] figure 2 A schematic flowchart of a method for determining the age of a character provided by Embodiment 2 of the present invention is given. This Embodiment 2 is optimized on the basis of the above-mentioned embodiments. In this embodiment, at least A frame of video image is embodied as: according to the video frame rate of the video, obtain each video image frame included in the video and the corresponding time point; divide the video image frame corresponding to each time point in seconds to the corresponding set of image frames; one frame is respectively selected from each set of image frames as a video image.

[0045] At the same time, this embodiment further optimizes the determination of the weighting coefficients of the human face images contained in each of the video images to: obtain the human face images contained in each of the video images, and obtain each of the human face images in the corresponding video image. The face coordinate information in the fa...

Embodiment 3

[0088] image 3 A structural block diagram of a device for determining a character's age provided by Embodiment 3 of the present invention is given. The device is suitable for determining the age attribution of a character. The device can be implemented by hardware and / or software, and is generally integrated in a computer on the device, such as image 3 As mentioned above, the device includes: an image acquisition module 30 , a coefficient determination module 31 , a probability determination module 32 and a category determination module 33 .

[0089] Wherein, the image acquisition module 30 is used to obtain at least one frame of video image from a given video;

[0090] The coefficient determining module 31 is used to determine the person weighting coefficient of the human face image that each described video image contains;

[0091] The probability determination module 32 is used to obtain the attribution probability values ​​corresponding to the characters in each of the...

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 figure age determination method and device, equipment and a storage medium. The method comprises the following steps: obtaining at least one frame of videoimage from a given video, and determining a figure weighting coefficient of a face image contained in each video image; obtaining a corresponding affiliation probability value of a figure in each faceimage under each preset age category; and according to the figure weighting coefficient of the figure in each face image and the affiliation probability value under each age category, determining a target age category to which the figure belongs in the video. According to the method, through the figure weighting coefficients of the figures in the face images, the weight of each figure appearing in the video can be determined; through combination with the affiliation probability value of the figure in the face image under each age category, the target age category to which the figure belongs in the video can be determined, effective identification of video audiences can be ensured through determination of the age category to which the figure belongs in the video, and thus the video recommendation precision is improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image recognition, and in particular, to a method, device, equipment, and storage medium for determining the age of a person. Background technique [0002] In the field of computer vision, person age recognition mainly refers to the use of related technologies to predict the age of people in input images or videos. With the rapid development of mobile Internet technology, face images are widely used in video recommendation, user authentication and intelligent security. The application of the technology is becoming more and more widespread, and the demand for age recognition of people in videos or images is also increasing. [0003] At present, the age recognition technology of people is mainly based on deep learning and uses face features combined with face recognition and other algorithms to predict the age of people. However, this type of technology usually only outputs the predict...

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): G06K9/00
CPCG06V40/16G06V40/178G06V20/40
Inventor 蔡佳然陈德健
Owner GUANGZHOU BAIGUOYUAN NETWORK TECH
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