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

Face image extraction method, storage medium and terminal equipment

A face image and image technology, applied in the field of image processing, can solve problems such as too large face area, inability to meet application scenarios, incomplete face area, etc.

Pending Publication Date: 2021-03-16
GREE ELECTRIC APPLIANCES INC +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is that the face area extracted by the existing face area extraction method is too large or too small, or the extracted face area is incomplete, which cannot meet the application scenarios

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 image extraction method, storage medium and terminal equipment
  • Face image extraction method, storage medium and terminal equipment
  • Face image extraction method, storage medium and terminal equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] In order to solve the above-mentioned technical problems existing in the prior art, an embodiment of the present invention provides a face image extraction method, wherein, the extended border line of the face area in this embodiment is based on the distance between the eyes and the corners of the mouth on the standard face image. , eye-nose distance, and mouth-nose distance are obtained by extending to the outside of the face in proportion.

[0070] figure 1 A flow chart of a face image extraction method according to an embodiment of the present invention is shown. refer to figure 1 , the face image extraction method that present embodiment provides, comprises the following steps:

[0071] S110, based on the face facial features detection model, detecting the positions of the eyes, nose and corners of the face from the face image;

[0072] S120, calculating the deflection direction and deflection angle of the line between the two eyes relative to the horizontal axis...

Embodiment 2

[0099] In order to solve the above-mentioned technical problems existing in the prior art, an embodiment of the present invention provides a method for extracting a human face image, wherein the extended human face area border line in this embodiment is the extended human face area border obtained in Embodiment 1 It is obtained by weighting the line and the border line of the central face area.

[0100] image 3 A flow chart of a method for extracting two face images according to an embodiment of the present invention is shown. refer to image 3 , the face image extraction method that present embodiment provides, comprises the following steps:

[0101] S210, based on the face facial features detection model, detecting the positions of the eyes, nose and corners of the face from the face image;

[0102] Specifically, the facial features detection model includes but not limited to MTCNN face features detection model, FaceNet face features detection model or MNIST face features ...

Embodiment 3

[0136]In order to solve the above-mentioned technical problems existing in the prior art, an embodiment of the present invention provides a face image extraction method, wherein, the embodiment of the present invention detects the eyes, nose and corners of the mouth on the face image based on the MTCNN facial features detection model and acquires The frame line of the central face area, the face image in this embodiment is a standard face image.

[0137] Figure 5 Show the flowchart of the three human face image extraction methods of the embodiment of the present invention, see Figure 5 , the face image extraction method that present embodiment provides, comprises the following steps:

[0138] S310, analyzing the face image based on the MTCNN face feature detection model;

[0139] S320, acquiring the coordinates of the eyes, the nose and the corners of the mouth on the face image;

[0140] S330. Obtain the frame line of the central face area;

[0141] S340. Calculate and ...

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 a human face image extraction method, a storage medium and terminal equipment, and the method comprises the steps: detecting the positions of eyes, nose and mouth corners of ahuman face from a human face image based on a human face five-sense-organ detection model; correcting the face image according to the included angle between the connecting line between the two eyes and the horizontal axis of the face image so as to obtain a standard face image; determining the eye distance, the mouth angle distance, the eye-nose distance and the mouth-nose distance based on the positions of the eyes, the nose and the mouth corner on the standard face image; correspondingly extending a preset multiple of eye distance, eye-nose distance, mouth angle distance and mouth-nose distance along a preset direction by taking the centers of the eyes, the central point between the eyes, the two mouth corners and the central point between the two mouth corners as starting points so as to obtain six positioning points; and determining an extended face area frame line according to the six positioning points, locking the target face area according to the extended face area frame line,obtaining an image of the target face area, and obtaining a complete face to meet application scene requirements.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a face image extraction method, a storage medium and a terminal device. Background technique [0002] In various applications such as face recognition, face modeling, and face detection, the extraction requirements of small face images will be involved. In many business scenarios such as face data management and face sample collection, reasonable face extraction results have broad application prospects. [0003] For the face area extraction method, part of the processing model uses the recognition results based on the key points of facial features, and extracts the face area according to the extraction method of fixed size outward expansion. The problem with this processing method is that, due to different shooting angles, when the face regions in the original image have different sizes, the extracted result of the face region will appear too large or too sm...

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
CPCG06V40/165G06V40/168
Inventor 谭泽汉郭旭峰周慧子谭龙田
Owner GREE ELECTRIC APPLIANCES INC