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

Acquisition Method of Infrared Partial Face Key Points Based on Binary Decision Tree

A face key point and decision tree technology, which is applied in the fields of biometric identification and information security, achieves great flexibility and practicability, avoids low processing speed, and has great practical value

Active Publication Date: 2020-03-24
BEIJING IRISKING
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] According to one aspect of the present invention, the present invention provides a method for acquiring infrared partial face key points based on a binary decision tree, which can solve the problem of face key point detection for infrared partial faces, and does not require a complete human face area, the key points of the face can be detected by using partial faces, and the present invention can also be run in real time on mobile phones

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
  • Acquisition Method of Infrared Partial Face Key Points Based on Binary Decision Tree
  • Acquisition Method of Infrared Partial Face Key Points Based on Binary Decision Tree
  • Acquisition Method of Infrared Partial Face Key Points Based on Binary Decision Tree

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The objects and functions of the present invention and methods for achieving the objects and functions will be clarified by referring to the exemplary embodiments. However, the present invention is not limited to the exemplary embodiments disclosed below, and may be implemented in various forms. The essence of the description is only to help those skilled in the relevant art comprehensively understand the specific details of the present invention.

[0031] figure 1 Show the flow chart of training classifier in the infrared partial face key point acquisition method based on binary decision tree according to the present invention, described training step comprises:

[0032] In step 101, samples are collected, human eyes are detected by a human eye detector, and the samples with detected human eyes are retained as pre-training samples. For example, opencv eye detector can be used to detect human eyes.

[0033] In step 102, on the basis of the collected pre-training samp...

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 present invention provides a method for acquiring key points of infrared local faces based on binary decision trees, comprising: a) importing a classifier obtained through binary decision tree training; b) detecting human eyes with a human eye detector, and estimating the local face area; c) according to the local face area estimated in step b, initialize the key points of the face; d) utilize the cascade set of the trained binary decision tree to predict the position of the key point of the face, the cascade set has S Level, each level has T said binary decision tree, enter the i(0

Description

technical field [0001] The invention relates to a biometric feature recognition and information security technology, in particular to an infrared partial human face key point detection method based on a binary decision tree. Background technique [0002] Face key point positioning is based on face detection, further positioning of eyes, eyebrows, nose, mouth and other contours, usually using the information near the key points and the relationship between each key point to locate, divided into model-based methods and regression-based methods. [0003] The model-based method is most represented by the ASM (Active Shape Model) method. The ASM method considers the texture and positional relationship constraints of dozens of facial feature points together to calculate a parameter model. The desired keypoints are detected from local features, but this method is very sensitive to noise. [0004] The regression-based method is another direction of ASM-related improvement, which i...

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 Patents(China)
IPC IPC(8): G06K9/00
CPCG06V40/171G06V40/172
Inventor 何召锋李茂林李星光李志林
Owner BEIJING IRISKING