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

Face region segmentation method, device, computer equipment and storage medium

A face area and area technology, applied in the field of face recognition, can solve the problem that the quality distribution of face images cannot be considered at the same time, and achieve the effect of accurate segmentation results

Active Publication Date: 2021-09-28
济南领信安全技术有限公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In related technologies, it is also impossible to perform image processing by considering the quality distribution of face images and the processing requirements of face images at the same time.

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 region segmentation method, device, computer equipment and storage medium
  • Face region segmentation method, device, computer equipment and storage medium
  • Face region segmentation method, device, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] In view of the above, this embodiment proposes a face region segmentation method, which is used to finely segment each local area (facial parts or organs) in a high-resolution face image, for example, given a high-resolution face image , perform pixel-level fine segmentation of facial contours, hairlines, eyes, noses, ears, eyebrows, mouths, and even accessories such as glasses, earrings, etc. figure 1 It is a flow chart of a face region segmentation method provided by an embodiment of the present invention. The method includes steps S10-S60.

[0063] S10: Obtain an average face template; based on the average face template, obtain an image quality requirement description map.

[0064] S20: Acquire a plurality of high-resolution face images; for each high-resolution face image, based on the image quality requirement description map, construct a boundary domain multi-dimensional data volume of the current face image, wherein the boundary domain multi-dimensional The dat...

Embodiment 2

[0106] Figure 5It is a schematic structural diagram of a face region segmentation device provided by an embodiment of the present invention. The device is used to implement the face region segmentation method provided in Embodiment 1, including a quality requirement acquisition module 510 , a multi-dimensional volume acquisition module 520 , a labeling module 530 , a model training module 540 and an area segmentation module 550 .

[0107] The quality requirement acquiring module 510 is used to acquire an average face template; based on the average face template, acquire an image quality requirement description map.

[0108] The multi-dimensional body acquisition module 520 is used to obtain multiple high-resolution face images; for each high-resolution face image, based on the image quality requirement description map, construct the boundary domain multi-dimensional data volume of the current face image, wherein, The boundary domain multidimensional data volume is a multidim...

Embodiment 3

[0136] Figure 6 It is a schematic structural diagram of a computer device provided by an embodiment of the present invention. Such as Figure 6 As shown, the device includes a processor 610 and a memory 620 . The number of processors 610 may be one or more, Figure 6 A processor 610 is taken as an example.

[0137] The memory 620, as a computer-readable storage medium, can be used to store software programs, computer-executable programs and modules, such as program instructions / modules of the face region segmentation method in the embodiment of the present invention. The processor 610 executes the software programs, instructions and modules stored in the memory 620 to implement the above method for face region segmentation.

[0138] The memory 620 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data...

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 face area segmentation method, device, computer equipment and storage medium. The method includes: obtaining an average face template, obtaining an image quality requirement description map; obtaining a plurality of high-resolution face images, and constructing a multidimensional data volume in the boundary domain of the current face image; performing pixel-level processing on each multidimensional data volume in the boundary domain Manual labeling; select a classifier model, and use the marked multiple boundary domain multidimensional data bodies as a data set to train the classifier model; obtain a high-resolution face image to be segmented, and construct the boundary of the current face image domain multi-dimensional data volume; using the trained classifier model to segment the boundary domain multi-dimensional data volume of the high-resolution face image to be segmented. The invention makes the face area segmentation more targeted, the segmentation result is more accurate, and the local rich detail information of the sub-area of ​​interest can be preserved to the greatest extent.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of face recognition, and in particular to a face region segmentation method, device, computer equipment, and storage medium. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] It is usually mentioned that the region of interest (Region Of Interest, ROI) of the face must be the face area. In recent years, more and more work not only requires the segmentation of accurate face ROI, but also requires fine segmentation of facial parts to segment the sub-region of interest (also called "face part ROI") on the face image. Or directly become a segmented face part. Finely segmenting face sub-regions of interest has important application value in face recognition, micro-expression recognition, beautification (automatic beautification and image editing), dynamic ...

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): G06T7/12G06T7/174
CPCG06T2207/20081G06T2207/20084G06T2207/30201G06T7/12G06T7/174
Inventor 杨光远郝凡昌张凯孔妍
Owner 济南领信安全技术有限公司