Key point positioning method and terminal

A positioning method and key point location technology, applied in the field of identification and positioning, can solve problems such as cost, difficulty in processing terminal hardware equipment, and multiple resources

Active Publication Date: 2016-04-20
TENCENT TECH (SHENZHEN) CO LTD
View PDF5 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, when using the existing face key point positioning method, although complex problems (various postures, expressions, lighting, occlusion, etc.) are decomposed into several simple problems to deal with, the accuracy of face key point tracking is significantly improved. , but according to different face categories, it is necessary to establish corresponding multiple face parameter shape models to achieve the final face key point positioning
Due to multiple face parameter shape models, it is bound to take up more memory storage space, and in the specific processing, it will consume more resources to process different face types corresponding to multiple face parameter shape models, thus impressing the terminal hardware. The processing of equipment brings processing difficulties

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
  • Key point positioning method and terminal
  • Key point positioning method and terminal
  • Key point positioning method and terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0085] An embodiment of the present invention provides a method for locating key points, such as figure 2 As shown, the method may include:

[0086] S101. When collecting a target object, it is detected that the target object is a face image, and a target detection area for face recognition and positioning is generated and marked on the i-th frame of the face image according to the preset configuration, i≥1.

[0087] In the embodiment of the present invention, the key point positioning method refers to the face key point positioning method, and the face key point positioning refers to accurately finding the position of the face key point through an algorithm. Among them, the key points of the face are some key points of the face with strong representation ability, such as eyes, nose, mouth and facial contour.

[0088] optional, such as image 3 In the schematic diagram of the initial key point positions of the human face image shown, there may be 49 key points in the embodi...

Embodiment 2

[0128] An embodiment of the present invention provides a method for locating key points, such as Figure 6 As shown, the method may include:

[0129] S201. When collecting a target object, it is detected that the target object is a face image, and a target detection area for face recognition and positioning is generated and marked on the i-th frame of the face image according to the preset configuration, i≥1.

[0130] In the embodiment of the present invention, the key point positioning method refers to the face key point positioning method, and the face key point positioning refers to accurately finding the position of the face key point through an algorithm. Among them, the key points of the face are some key points of the face with strong representation ability, such as eyes, nose, mouth and facial contour.

[0131] optional, such as image 3 In the schematic diagram of the initial key point positions of the human face image shown, there may be 49 key points in the embodi...

Embodiment 3

[0165] An embodiment of the present invention provides a method for locating key points, such as Figure 8 As shown, the method may include:

[0166] S301. When i>1, when the target object is collected, it is detected that the target object is a face image, and according to the position of the face key point of the i-1th frame of the face image, the face image that can contain the i-1th frame is obtained At least one face detection area of ​​face key points.

[0167] In the embodiment of the present invention, the key point positioning method refers to the face key point positioning method, and the face key point positioning refers to accurately finding the position of the face key point through an algorithm. Among them, the key points of the face are some key points of the face with strong representation ability, such as eyes, nose, mouth and facial contour.

[0168] optional, such as image 3In the schematic diagram of the initial key point positions of the human face ima...

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 key point positioning method and a terminal. The method comprises the steps of detecting a target object as a face image during the collecting process of the target object; generating a target detecting region on the face image of the i frame for human face recognition and location according to a preset configuration and annotating the target detecting region, wherein i is larger than or equal to 1; when i is larger than 1, estimating the key point information of a human face based on the face image of the i frame according to the similarity matching strategy between a previous frame and the current frame so as to obtain the category of the human face for the face image of the i frame; according to the category of the human face for the face image of the i frame, determining a first initial shape out of a plurality of preset candidate initial shapes; and calculating the position of an initial face key point in the face image of the i frame according to the target detecting region and the first initial shape.

Description

technical field [0001] The invention relates to identification and positioning technology in the field of computer vision, in particular to a key point positioning method and a terminal. Background technique [0002] When users collect target objects, they will carry out various identifications. For example, taking face recognition as an example, computer face recognition endows the computer system with the ability to identify unknown persons based on faces, making the computer system based on the known face sample library , using computer analysis and pattern recognition technology to identify or verify one or more faces from static or dynamic scenes, this technology has been widely used in public security, identification and other occasions. The face recognition system includes steps such as face detection, face key point positioning, recognition and tracking, and face key point detection and tracking is a very important part of face recognition, and it is also the face ve...

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): G06K9/00G06K9/46
CPCG06V40/166G06V40/171G06V40/172G06V10/462
Inventor 宫鲁津
Owner TENCENT TECH (SHENZHEN) 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