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

Single image spiral symmetric structure detection method based on matching feature triplet

A technology of matching features and detection methods, applied in the field of computer vision, can solve problems such as insufficient detection of non-specific helical symmetry structures

Active Publication Date: 2017-07-04
北京宏博知微科技有限公司
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these works are not sufficient to solve the task of detecting non-specific helical symmetry structures in a single image

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
  • Single image spiral symmetric structure detection method based on matching feature triplet
  • Single image spiral symmetric structure detection method based on matching feature triplet
  • Single image spiral symmetric structure detection method based on matching feature triplet

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] In order to make the purpose, technical solution and advantages of the present invention clearer, the implementation manners of the present invention will be further described in detail below.

[0040] No current symmetry detection method attempts to detect the entire generalized helical symmetry structure from non-special class real images. To fill this gap, this method proposes a rational and efficient approach to this challenging problem. The method of matching feature triplets (MRFs) was used to detect non-specific helical symmetry structures. Relying on the value-degree Hough voting, it can reliably obtain the main spiral centroid, the corresponding growth direction, the same growth rate and the initial radius set of the generalized spiral symmetric structure. At the same time, a large number of experiments have been done to prove the effectiveness and superiority of this method.

[0041] The present invention addresses the detection of helical symmetry structure...

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 method for detecting the spiral symmetric structure of a single image based on a matching feature triple. The method includes the following steps: determining the centroid of the main spiral; calculating the candidate value of the spiral growth rate; determining the direction of the spiral growth; determining the main spiral growth rate; computes initial set of radii; reconstructs helix group from main helix centroid, helix growth rate, direction of helix growth, and initial set of radii. This method can effectively obtain the main spiral center, growth direction, growth rate and initial radius set of a spiral symmetrical structure from a single image. A large number of experiments have been carried out on artificial images and natural scenes to prove the effectiveness and superiority of this method.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a method for detecting spiral symmetric structures in a single image based on matching feature triplets, which can quickly and effectively detect spiral symmetric structures in artificial images and natural scenes. Background technique [0002] Generally speaking, the spiral law [1, 2] exists in a large number no matter in nature or man-made things. Since the human visual system is very sensitive to symmetric structures, and under different imaging conditions, geometric symmetric structures have many characteristics that are the same, so the detection of symmetric structures is very important in understanding the image structure and content [3, 4]. . Recently, many effective methods have been proposed that are able to detect specific symmetric structures on a single image [4-6]. Meanwhile, symmetry detection is also used in many vision tasks, such as image segmentation [7, 8], ob...

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): G06T7/68G06K9/64G06K9/46
CPCG06V10/40G06V10/757
Inventor 冯伟孙济洲王建东张乾
Owner 北京宏博知微科技有限公司