Method and device for determining initial face shape in face alignment algorithm
A technology of face alignment and determination method, which is applied in the field of image processing and can solve problems such as low accuracy
Active Publication Date: 2021-01-19
杭州西纬软件科技有限公司
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
It can be seen that the determination method of the initial face shape in the existing face alignment algorithm is to calculate the average value of all samples, and its precision is low, so that the follow-up algorithm needs to carry out the face shape to obtain the accurate position of the key points. Multiple regression, so it is necessary to provide a method for determining the initial face shape in the face alignment algorithm
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. The components of the embodiments of the invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present invention.
[0021] It should be noted that like numerals and let...
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
Login to View More Abstract
The present invention relates to the technical field of image processing, in particular to a method, device, intelligent terminal and computer-readable storage medium for determining an initial face shape in a face alignment algorithm. The method includes: calculating the average face shape of sample image sets of different categories, obtaining a target face image, and collecting a predetermined number of key points on the target face image, and then according to the positions of the key points and the average The position of the point on the face shape determines the average face shape corresponding to the target face image, obtains the binarized image of the skin area of the target face image, and finally adjusts the average face shape corresponding to the target face image according to the binarized image. Face shape Get the initial face shape of the target face image in the face alignment algorithm. It can be seen that this solution determines the average face shape of the target face image through two aspects, making the final initial face shape more accurate, so as to better reduce the regression process of the subsequent algorithm.
Description
technical field [0001] The present invention relates to the technical field of image processing, in particular to a method and device for determining an initial face shape in a face alignment algorithm. Background technique [0002] At present, the face alignment algorithm is a basic algorithm in many application fields, such as face thinning, etc., through the face alignment algorithm, multiple key points on the face can be determined more accurately, so as to facilitate subsequent algorithm processing. The existing face alignment algorithm mainly uses cascaded multi-level regression to gradually approach the final desired result. Specifically, the initial face shape is obtained by averaging the face shapes of all face sample images, and then Multiple regressions are performed on the initial face shape to determine the final face shape. It should be noted that the face shape is represented by multiple key points selected on the face image. It can be seen that the determina...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
CPCG06V40/161
Inventor 柯智捷
Owner 杭州西纬软件科技有限公司