Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Robustness feature description method for images with noise

An image feature and robust technology, applied in image enhancement, image data processing, instruments, etc., can solve problems such as loss of function, lack of noise resistance, inability to accurately describe local features of images, etc., and achieve high robustness Effect

Inactive Publication Date: 2014-06-25
NAT UNIV OF DEFENSE TECH
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the image is noisy, these descriptors lose their original function and cannot accurately describe the local features of the image, which shows that these local feature descriptors do not have noise resistance

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
  • Robustness feature description method for images with noise
  • Robustness feature description method for images with noise
  • Robustness feature description method for images with noise

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Such as figure 1 Shown, below in conjunction with embodiment the method of the present invention is described:

[0038] First, with a certain pixel point (x i ,y i ) as the center for sample point sampling, the sampling schematic diagram is as follows figure 2 shown. In this embodiment, the sampling radius is 2, the number of sampling points is 16, and the sample point vector is T i =[t 1 ,t 2 ,...,t 16 ]. The calculation formula for the position of the pth sample point is as follows:

[0039] (x p ,y p )=(x i +2cos(2πp / 16),y i -2sin(2πp / 16))

[0040] In a digital image, it is not guaranteed that the coordinates of all pixel points fall on the integer point, so the existing bilinear interpolation algorithm is used to calculate the gray value of the point that does not fall completely on the pixel position.

[0041] Secondly, for the obtained sample point vector T i Perform a one-dimensional discrete Fourier transform to obtain the local feature vector V ...

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 robustness feature description method for images with noise, and belongs to the field of digital image processing. Firstly, a sampling method based on a local binary pattern is adopted to sample local images to construct sample point vectors; secondly, one-dimensional Fourier transformation is carried out on the collected sample point vectors to obtain local feature descriptors based on frequency domains; ultimately, a low-frequency filter is used, and a low-frequency part of feature vectors is selected as a final local feature descriptor. Because of frequency domain conversion and low-frequency filtering, the feature descriptor has good robustness to noise, and rotational invariance and gray scale invariance of an LBP descriptor remain.

Description

technical field [0001] The invention relates to the field of digital image processing, in particular to a local feature description method for a noisy image under the condition that the image is polluted by noise, and the feature descriptor has good robustness to noise. Background technique [0002] Local features start from the local structure of the image and use local information to construct a descriptor that can describe the local image. Local features describe the regional information in the image. Usually, because of the differences in pixels, colors or textures between regions, local features reflect unique descriptiveness. Describing images with local features can transform the complex image matching problem into a feature vector measurement problem, thereby improving the speed and robustness of the algorithm. At present, many local feature descriptors have been proposed, the most famous is the scale-invariant feature transform (SIFT) descriptor proposed by David L...

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
IPC IPC(8): G06T5/00
Inventor 刘煜张茂军王炜熊志辉徐玮肖华欣
Owner NAT UNIV OF DEFENSE TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com