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

Polar coordinate Fourier transform based rotation invariance image characteristic extraction method

A technology of image feature extraction and Fourier transform, which is applied in the field of rotation invariant image feature extraction, can solve problems such as difficult detection of rotation-changing targets, and achieve the effect of improving accuracy

Active Publication Date: 2014-03-19
WUHAN UNIV
View PDF3 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The current image features are difficult to detect the target of the rotation change

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
  • Polar coordinate Fourier transform based rotation invariance image characteristic extraction method
  • Polar coordinate Fourier transform based rotation invariance image characteristic extraction method
  • Polar coordinate Fourier transform based rotation invariance image characteristic extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The method of the present invention obtains the CHOG feature of the image based on the circular block strategy, performs polar coordinate transformation on the CHOG feature of the image, and performs two-dimensional discrete Fourier transform on the transformed CHOG feature, and the obtained Fourier transform coefficient is the Invariant image features.

[0035] The technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0036] figure 1 Be the concrete flowchart of the inventive method, this method comprises steps:

[0037] Step 1, get the gradient of the image.

[0038] The [-1,0,1] template is used to perform convolution calculation on the image to obtain the gradient in the horizontal direction and the vertical direction, and the length of the image gradient is taken as the calculation result of the horizontal gradient and vertical gradient, respectively.

[0039] Step 2, obtain the gradient di...

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 provides a polar coordinate Fourier transform based rotation invariance image characteristic extraction method. The method comprises the steps of, step one, obtaining image gradients and obtaining image gradient directions according to the image gradients; step two, performing normalization processing on the image gradient directions; step three, extracting image CHOG characteristics base on the normalized image gradient directions; step four, performing polar coordinate Fourier transform on the image CHOG characteristics, and extracting transformed Fourier coefficient amplitudes as rotation invariance image characteristics. According to the method, shapes of objects in the images can be well described through the CHOG characteristics, and by the rotation invariance image characteristics obtained through polar coordinate Fourier transform performed on the image CHOG characteristics, detection of rotation targets can be achieved, and certain meaning is provided for the improvement of target detection accuracy.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, in particular to a rotation invariant image feature extraction method based on polar coordinate Fourier transform. Background technique [0002] Many problems in digital image processing, such as: image matching, object recognition, three-dimensional reconstruction, can be attributed to the extraction and recognition of image features. These problems can be well solved by extracting locally invariant image features. The local invariance feature takes the local area of ​​the image as the processing unit, and has good invariance to the optical and geometric changes of the image. On the one hand, local invariant features are not easily affected by translation, rotation, scaling, and lighting, and on the other hand, they can largely avoid the influence of complex backgrounds on features. Compared with global features, local features are more targeted, more flexible in locati...

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): G06K9/00G06K9/46
Inventor 肖志峰刘清唐阁夫
Owner WUHAN UNIV
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