Image characteristic points positioning method and device
An image feature point and positioning method technology, applied in the field of image processing, can solve the problems of low efficiency and limited application of image feature point positioning, and achieve the effect of wide application and high efficiency
Active Publication Date: 2009-10-14
BEIJING VIMICRO ARTIFICIAL INTELLIGENCE CHIP TECH CO LTD
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0011] Embodiments of the present invention provide a method and device for locating image feature points to solve the problems of low efficiency and limited application of image feature point locating in the prior art
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
[0033] The embodiment of the present invention provides a method and device for locating feature points of an image by taking locating feature points of eyes of a person in an image as an example. The embodiment of the present invention does not rely on the eye positioning algorithm of the face detection algorithm, and overcomes the limitation of the prior art that all faces of people are required to be presented in the image.
[0034] The specific implementation manners of the embodiments of the present invention will be introduced below in conjunction with the accompanying drawings.
[0035] see figure 2 , the method for locating eye feature points in an image provided by an embodiment of the present invention includes:
[0036] S201. Use a pre-trained binocular area detector to detect a binocular area on an input image.
[0037] S202. Determine a left-eye search area and a right-eye search area on the binocular area.
[0038] S203. Use a left-eye local feature detector ...
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 an image feature point positioning method and device, which are used to solve the problems of low image feature point positioning efficiency and limited application in the prior art. The method of the present invention includes: using a pre-trained binocular area detector to detect the binocular area on the input image; determining the left eye search area and the right eye search area on the binocular area; and using the left eye local feature detector Detecting the left-eye search area to obtain left-eye candidate positions; using a right-eye local feature detector to detect the right-eye search area to obtain right-eye candidate positions; selecting several left-eye candidate positions and right-eye candidate positions performing pairing; and, using a binocular area verifier to verify the pairs of left-eye candidate positions and right-eye candidate positions to determine the left-eye position and the right-eye position. The invention is used for locating the feature points in the image, improving the image locating rate and expanding the application range of the image locating.
Description
technical field [0001] The present invention relates to the technical field of image processing, in particular to a method and device for locating image feature points. Background technique [0002] In the field of image understanding and computer vision technology, various applications including face recognition and human-computer interaction need to quickly and accurately locate the position of the human eye in the image. In order to detect the eyes at any position and size in the image, the image must be searched, and the specific position of the eye in the image has been located. Algorithms for locating eyes in images in the prior art, see figure 1 ,include: [0003] S101. Obtain face position and size information through face detection, and determine a left-eye search area and a right-eye search area in a statistical manner. [0004] That is, determine the range of possible positions of the left eye and the right eye in the image, and call each possible position a pr...
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): G06K9/32G06K9/00G06K9/62
Inventor 邓亚峰黄英
Owner BEIJING VIMICRO ARTIFICIAL INTELLIGENCE CHIP TECH CO LTD