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

Rotation-invariant Image Feature Extraction Method Based on Polar Coordinate Fourier Transform

An image feature extraction and Fourier transform technology, which is applied in the field of rotation invariant image feature extraction, can solve problems such as difficult to detect the target of rotation change, and achieve the effect of improving accuracy

Active Publication Date: 2016-07-13
WUHAN UNIV
View PDF3 Cites 0 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
  • Rotation-invariant Image Feature Extraction Method Based on Polar Coordinate Fourier Transform
  • Rotation-invariant Image Feature Extraction Method Based on Polar Coordinate Fourier Transform
  • Rotation-invariant Image Feature Extraction Method Based on Polar Coordinate Fourier Transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The method of the present invention is based on the circular block strategy to obtain the CHog feature of the image, 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 coefficients are rotated Invariant image characteristics.

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

[0036] figure 1 It is a specific flowchart of the method of the present invention, and the method includes the steps:

[0037] Step one is to obtain the gradient of the image.

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

[0039] Step 2: Obtain the gradie...

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 rotation-invariant image feature extraction method based on polar coordinate Fourier transform, comprising the steps of: Step 1, obtaining the image gradient, and obtaining the gradient direction of the image according to the image gradient; Step 2, determining the gradient direction of the image Carry out normalization processing; Step 3, extract the CHOG feature of image based on the image gradient direction after normalization processing: Step 4, carry out polar coordinate Fourier transform to the CHOG feature of image, extract the magnitude of Fourier coefficient after transformation The value is a rotation invariant image feature. The invention adopts the CHOG feature to describe the shape of the object in the image well, performs polar coordinate Fourier transform on the CHOG feature of the image, and the obtained rotation invariant image feature can realize the detection of the rotating target, which is helpful for improving the accuracy of target detection a certain meaning.

Description

Technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates 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, target recognition, and three-dimensional reconstruction, can be attributed to the problem of image feature extraction and recognition. These problems can be solved well by extracting local invariant image features. The local invariance feature uses a local area of ​​the image as a processing unit, which has good invariance to the optical and geometric changes of the image. On the one hand, local invariance features are not easily affected by translation, rotation, scaling, and illumination. 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 flexi...

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