Image stable characteristic point extracting method and device

An image feature point and image stabilization technology, applied in the field of image processing, can solve the problems of not quantifying the stability of image feature points, not supporting image scale changes, low recurrence rate of image feature points, etc.

Inactive Publication Date: 2011-06-15
PEKING UNIV FOUNDER GRP CO LTD +2
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] (2) The Harris corner method directly improves the Moravec method, uses the Gaussian function as the filter function, and uses the first-order Taylor expansion to represent changes in all directions, but the Harris corner method does not support image scale changes , that is, the scaling of the image
[0008] (4) The SIFT (Scale Invariant Feature Transform) method simplifies the construction of the scale space in the Harris Laplacian method, and uses the local extremum of the difference filter function to describe the scale invariance of the image feature points. The advantage is that the calculation speed is fast, but The disadvantage is that the recurrence rate of image feature points is lower than the former, which also limits its application in occasions that require a higher recurrence rate.
[0009] While implementing the technical solution of the present invention, the inventor found that the prior art has at least the following defects: the current extraction methods for various image feature points have not quantified the stability of the image 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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image stable characteristic point extracting method and device
  • Image stable characteristic point extracting method and device
  • Image stable characteristic point extracting method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] Embodiments of the present invention provide a method for extracting image stabilization feature points, such as figure 1 As shown, the method includes:

[0051] Step 11, filtering the read-in digital image lattice data to construct an image scale space;

[0052] Step 12. Obtain a scale-invariant set of image feature points through regional threshold control;

[0053] Step 13. Calculating a stabilization factor of the image feature points, and obtaining a set of image stabilization feature points through threshold control according to the stabilization factors of the image feature points.

[0054]According to the principle that the classical SIFT method approximates the image scale space, an image feature point extraction method that also has the property of scale invariance is constructed. In a nutshell, the scale space of the image is constructed by scaling down the filtered image sequentially, the feature points are obtained by checking the local area extreme point...

Embodiment 2

[0059] Embodiments of the present invention provide a method for extracting image stabilization feature points, such as image 3 As shown, the method includes:

[0060] Step 21, read in digital image dot matrix data;

[0061] First, read in the 2-dimensional digital image I(x, y).

[0062] Step 22: Construct the scale space of the image by successively scaling down the filtered image.

[0063] Use cubic interpolation to expand I(x, y) to twice the size, denoted as I' 0 (x,x). Will I' 0 (x, y) and the Gaussian filter function with a window of 5×5 G ( x , y , σ ) = 1 2 πσ 2 e - ( x 2 + y 2 ...

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 an image stable characteristic point extracting method and device, and relates to the field of image processing and is capable of quantizing the stability of image characteristic points. The method comprises the following steps of: filtering read digital image dot matrix data and constructing an image dimension space; obtaining a point set of image characteristic points with unchanged dimensions through region threshold value control; and calculating stable factors of the image characteristic points, and obtaining the point set of the image characteristic points through threshold value control according to the stable factors of the image characteristic points. The image stable characteristic point extracting method and device are applied to image recognition and image characteristic extraction.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method and device for extracting image stabilization feature points. Background technique [0002] At present, digital images are more commonly used information carriers. From a graphics point of view, if a certain pixel in the image is an image feature point, then within a certain distance, the point must change drastically in a certain direction or in multiple directions, for example, the "group stain" area is easy to extract Image feature points. In many digital image processing technologies, image feature points are like "landmarks" and play a key role in local image localization. The image processing technologies listed below all rely on image feature point matching or resynchronization to complete their important tasks, including: image recognition technology, content-based image retrieval technology, image stitching technology, image matching technology and digital imag...

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 Applications(China)
IPC IPC(8): G06K9/46G06T5/00
Inventor 王高阳陈绪东亓文法李晓龙杨斌
Owner PEKING UNIV FOUNDER GRP CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap