Method and device for locating feature points
A feature point positioning and feature point technology, which is applied in three-dimensional object recognition, instrument, character and pattern recognition, etc., can solve the problem of unable to effectively deal with the problem of multi-pose face feature point positioning.
Active Publication Date: 2018-03-27
HUAWEI TECH CO LTD
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, this type of technology cannot effectively deal with the localization of multi-pose face feature points.
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
[0068] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0069] figure 1 is a schematic flow chart of a method for feature point location according to an embodiment of the present invention. figure 1 The method 100 includes:
[0070] 110. Acquire an image I, where the image I includes at least one feature point.
[0071] 120. Based on the 3D pose binarization feature of the image I, the preset initial 3D pose parameter θ 0 The regression operation is performed to obtain the converged three-dimensional attitude param...
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 invention discloses a method and a device for locating feature points. The method includes: acquiring an image I, and the image I includes at least one feature point; performing a regression operation on a preset initial three-dimensional attitude parameter θ0 based on the three-dimensional attitude binarization feature of the image I to obtain a converged three-dimensional attitude parameter θ; according to the convergence The three-dimensional attitude parameter θ of the initial layer 1 feature point set is determined based on the first layer shape binarization feature of the image I, and the shape parameter of the initial layer 1 feature point set is regressed to obtain the converged The shape parameter V1 of the feature point set of the first layer. In the embodiment of the present invention, the three-dimensional pose and the feature point set are modeled separately, and then the initialization parameters of the feature point set model are selected according to the output result of the three-dimensional pose, so that the feature point positioning in a multi-pose scene can be realized, and at the same time, it has a higher accuracy and faster processing speed.
Description
technical field [0001] The present invention relates to the field of image processing, and more specifically, to a method and device for feature point positioning. Background technique [0002] Automatic facial feature localization is an important research topic in the field of computer vision. At present, in the latest face recognition technology, all face images that are input for automatic recognition need to be located by face feature points to realize the extraction of local face features and the geometric correction of faces. For example, in the face recognition technology adopted by Microsoft's somatosensory devices, the positions of five key feature points (left and right eyes, left and right mouth corners, and nose tip) are used to extract and recognize facial features. [0003] With the application of the markerless facial expression capture system in the film and television special effects industry, scenes similar to "Avatar" special effects have become a widely ...
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): G06K9/66
CPCG06V40/164G06V40/169G06V20/64G06V40/165G06V40/171
Inventor 张维刘健庄许春景
Owner HUAWEI TECH CO LTD