Rejecting method of wrong matching with fused point-wire characteristics
A feature fusion and error matching technology, which is applied in image data processing, instruments, character and pattern recognition, etc., can solve problems such as error matching, and achieve the effect of simple calculation, universality, computational complexity and excellent efficiency
Active Publication Date: 2018-07-20
HENAN POLYTECHNIC UNIV
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0010] The present invention aims at the problem of wrong matching existing in the existing curve matching and point matching algorithms, and aims to provide a matching method that combines point and line features
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
[0025] Such as figure 1 Shown is the flow chart of the false matching elimination method for point-line feature fusion of the present invention, including: collecting images and inputting them into the computer, matching feature points in the images, matching feature curves in the images, determining the supporting area of the matching curves, and obtaining the corresponding Match point pairs in the support area, calculate the minimum distance from the feature point to the curve in the curve support area, eliminate the wrong curve match according to the difference degree of the matching curve pair, and eliminate the wrong point match according to the difference degree of the matching point pair.
[0026] The specific implementation details of each step are as follows:
[0027] Step S1: Take two different images of the same scene from different angles and input them into the computer.
[0028] Step S2: Use SIFT technology to detect and match feature points, and obtain a set ...
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 relates to a rejecting method of wrong matching with fused point-wire characteristics. The rejecting method of wrong matching with fused point-wire characteristics includes the steps: shooting two different images of the same scene from different angles, and inputting the images into a computer; performing characteristic point detection and matching by means of the SIFT technology; performing curve matching by means of a curve descriptor; determining a support region of each matching curve; acquiring the matched point pair in the corresponding support region, of the matching curve; calculating the minimum distance from the characteristic point to the curve in the support region of the corresponding curve; according to the difference degree of the matched curve pairs, rejecting the wrong curve matching; and according to the difference degree of the matched curve pairs, rejecting the wrong point matching. The rejecting method of wrong matching with fused point-wire characteristics can simply and quickly reject the wrong matching in the images, and has universality.
Description
technical field [0001] The invention relates to the field of image feature matching in computer vision, in particular to point matching and line matching methods in image matching. Background technique [0002] Feature matching technology has important applications in the fields of image retrieval, object recognition, video tracking and augmented reality. At present, the existing curve matching methods mainly include the following two types, the first type is the matching method based on the curve shape, and the second type is the matching method based on the image content [1-3] . When the local deformation is large, the two methods will generate more mismatches, and the matching accuracy and total number cannot reach the expected effect. Therefore, removing false matches from existing matching results is a basic problem in the fields of computer vision, pattern recognition, etc., and it should have a wide range. [0003] In the existing methods, there are many studies on...
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 IPC IPC(8): G06K9/62G06K9/46G06T7/13
CPCG06T7/13G06V10/752G06V10/757G06V10/462G06F18/253
Inventor 刘红敏魏玉慧王国东罗军伟王静贾利琴雒芬霍占强姜国权王志衡
Owner HENAN POLYTECHNIC UNIV