Age grouping method based on facial image features

A face image and face alignment technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve problems that cannot meet daily life, age classification is rough, single, etc., to facilitate modeling and calculation, dimensionality Moderately sized, accuracy-enhancing effects

Inactive Publication Date: 2017-07-04
苏州工业园区洛加大先进技术研究院
View PDF14 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Chinese patent (Patent No. 201310630395.9) discloses a method and system for pushing smart TV services based on age groups, which needs to collect statistics on users’ viewing information and usage information to push programs and applications suitable for age groups. Improve the user experience of smart TVs, but cannot intelligently select the content of advertisements
[0005] Another example is Chinese patent (Patent No. 201510077017.1, 201510008466.0) which discloses a method for automatically playing TV programs for children, a TV set and a system, and a disclosed system and method for controlling children's viewing behavior for digital TV set-top boxes. Playing TV programs suitable for children to watch for children is relatively simple
[0006] What Chinese patents (Patent Nos. 201410738512.8, 201110195665.9, 201110442676.2, 201210042789.8, 200910131059.3, 201410242917.2, 200910032756.3) are disclosed are different methods for daily life that cannot be roughly estimated age, and the above-mentioned classification of different methods of age identification

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
  • Age grouping method based on facial image features
  • Age grouping method based on facial image features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0030] In order to achieve the purpose of the present invention, as Figure 1 to Figure 2 As shown, in one of the embodiments of the present invention, a method for age segmentation based on facial image features is provided, including the following steps:

[0031] S1. Obtaining a face image;

[0032] S2, face image preprocessing;

[0033] S3, extracting the LBP feature of the face image;

[0034] S4. Form a training image set according to all the extracted LBP features and perform training to obtain an age segmentation model.

[0035] Wherein, in step S1, a camera or a face detector is used to intercept a face image from a database.

[0036] The above-mentioned face image preprocessing includes the following steps:

[0037] S10, intercepting multiple key points of the face image and using the key points to perform face alignment;

[00...

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 age grouping method based on facial image features. The method comprises the steps that S1, a facial image is acquired; S2, the facial image is preprocessed; S3, LBP features of the facial image are extracted; and S4, a training image set is formed according to all the extracted LBP features, and training is performed to obtain an age grouping model. Compared with the prior art, facial alignment is performed on the facial image by use of key points to obtain a front face image, so that the LBP features are convenient to extract, and accuracy is improved; the dimension is appropriate, and modeling and computing are convenient; the age grouping model can be applied to various occasions to realize age-based constraint, control and auxiliary lamp application, recognition accuracy is high, higher intellectualization is achieved, and therefore daily demands of people are met.

Description

technical field [0001] The invention belongs to the technical field of computer applications, and in particular relates to an age segmentation method based on facial image features. Background technique [0002] At present, there are more and more age-based applications in daily life, such as age-based coercion, control and assistance. [0003] In the prior art, for example, the Chinese patent (Patent No. 201410242566.5) discloses a method and system for intelligent push of information media, using the existing opencv and openBR to identify the collected pictures, and the accuracy of face recognition is not high . [0004] Chinese patent (Patent No. 201310630395.9) discloses a method and system for pushing smart TV services based on age groups, which needs to collect statistics on users’ viewing information and usage information to push programs and applications suitable for age groups. Improve the user experience of smart TVs, but cannot intelligently select the content o...

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): G06K9/00
CPCG06V40/178G06V40/16G06V40/168
Inventor 周文生刘平
Owner 苏州工业园区洛加大先进技术研究院
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