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

Face recognition method and face recognition system

A face recognition system and face recognition technology, applied in the field of face recognition methods and face recognition systems, can solve problems such as difficult adjustment, time-consuming and laborious collection of samples, complex training process parameters, etc., to achieve flexible recognition and fast calculation speed , high accuracy effect

Active Publication Date: 2019-05-07
TENCENT TECH (SHENZHEN) CO LTD +1
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the purpose of the present invention is to provide a face recognition method and a face recognition system, which can solve the problem of time-consuming and labor-intensive collection of samples in the machine learning algorithm in the prior art, and the training process involves complex parameters and is not easy to follow the user's behavior. Technical issues that are adjusted due to changes, and then affect the accuracy and flexibility of the recognition results

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
  • Face recognition method and face recognition system
  • Face recognition method and face recognition system
  • Face recognition method and face recognition system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] see figure 1 , shows the basic flowchart of the face recognition method. The face recognition method is usually implemented in a terminal device.

[0032] The face recognition method is used to detect occluded areas in the human face, wherein the occluded area in the present invention mainly refers to hair, and can also detect occluded objects such as beards and glasses, which will not be repeated here.

[0033] The face recognition method includes:

[0034] In step S101, face detection is performed on the image, and the detected faces are marked.

[0035] Wherein, the human face can be marked by a marking frame, and the marking frame is generally a rectangular frame, which frames the area from the forehead to the chin, and from the left to the ears of the face. The way it is implemented, such as through the open source face detection algorithm of OpenCV (OpenSource Computer Vision Library, open source computer vision library), performs face detection on images.

[...

Embodiment 2

[0058] see figure 2 , shows a detailed flowchart of the face recognition method. The face recognition method is usually implemented in a terminal device.

[0059] figure 2 steps in the figure 1 Different start with S2, with figure 1 The same ones still start with S1 to show their differences.

[0060] The face recognition method is used to detect the occluded area in the face, comprising:

[0061] In step S201, face detection is performed on the image, and the detected faces are marked with a marking frame.

[0062] Specifically, the forming step of the mark frame includes:

[0063] (1) Through Opencv's open source face detection algorithm, face detection is performed on the image;

[0064] (2) mark the detected faces by a mark frame; and

[0065] (3) Obtain the coordinate value of the left vertex and the coordinate value of the right vertex of the marked frame.

[0066] In step S102, the faces in the marked frame are positioned to obtain the center point of the lef...

Embodiment 3

[0091] see image 3 , which is a schematic diagram of the basic modules of the face recognition system. The face recognition system is usually implemented in a terminal device.

[0092] The face recognition system 300 is used to detect the occluded area in the human face, wherein the occluded area in the present invention mainly refers to the hair, it can be understood that based on the face recognition system of the present invention, beards can also be detected , glasses and other obstructions, because the inference method is simple, it will not be repeated here.

[0093] The face recognition system 300 includes: a detection module 31 , a positioning module 32 , a selection module 33 , a pixel module 34 , and an area module 35 .

[0094] Specifically, the detection module 31 is configured to perform face detection on the image, and mark the detected faces.

[0095] Wherein, marking may be performed by a marking frame, and the marking frame generally adopts a rectangular f...

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 provides a face recognition method and a face recognition system, which are used to detect the occluded area in the face, including: performing face detection on the image, and marking the detected face; marking the marked face Positioning is performed to obtain the center point of the left eye and the center point of the right eye respectively; the center point of the left eye, the center point of the right eye, and two vertices on the upper side of the marker frame constitute a geometric area; the calculation of the The chroma component of each pixel in the geometric area; the difference pixels whose chroma components are not equal to the preset chroma are filtered out, and the interval corresponding to the difference pixels is counted as the occlusion area. The present invention counts the pixels different from the skin color in the geometric area formed by the marked frame and the eyes as the occluded area, without collecting samples, training parameters, and not being interfered by user behavior, and has high accuracy and fast calculation speed , and recognize the advantages of flexibility.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a face recognition method and a face recognition system. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. Video cameras or cameras are usually used to collect images or video streams containing human faces, and automatically detect and track human faces in the images. It can be widely used in identification, liveness detection, lip language recognition, creative camera, face beautification, social platforms and other scenarios. [0003] Among them, the accuracy of face recognition will be affected by various factors such as photographing posture (front or side), light (day or night), occluders (hair, glasses, beard), etc. Among them, the factor that most affects the accuracy rate is the long vertical hair between the eyebrows and the corners of the eyes. [0004] In this regard, a ...

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
CPCG06V40/162G06V40/165
Inventor 谭国富
Owner TENCENT TECH (SHENZHEN) CO LTD