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

Division method for extracted watershed SAR image with threshold method and marking

A technology for marking watersheds and image segmentation, which is applied in the field of image processing to achieve the effects of ensuring accuracy, reducing storage capacity, and reducing over-segmentation

Inactive Publication Date: 2009-10-14
XIDIAN UNIV
View PDF0 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is: to overcome the over-segmentation problem caused by the application of existing image segmentation algorithms to SAR images, and to propose a watershed SAR image segmentation method based on threshold method marker extraction. The watershed markers are derived from Otsu threshold method segmentation The image can guarantee the accuracy of the marking, greatly eliminate the influence of texture information, and effectively solve the over-segmentation problem of the watershed image segmentation algorithm

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
  • Division method for extracted watershed SAR image with threshold method and marking
  • Division method for extracted watershed SAR image with threshold method and marking
  • Division method for extracted watershed SAR image with threshold method and marking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] refer to figure 1 , the concrete realization process of the present invention is as follows:

[0032] 1. Perform Gaussian low-pass filtering on the original image Img to obtain the filtered image GImg;

[0033]The invention uses Gaussian low-pass filter to remove the details or noise part of the image. The working principle of the Gaussian low-pass filter can be analyzed in the frequency domain. The basic idea is to suppress the components of the image in the high-frequency range of the Fourier space, while leaving the low-frequency components unaffected, thereby changing the frequency distribution of the output image to achieve the purpose of filtering. The basic steps are: (1) use (-1) x+y Multiply the input image to perform center transformation; (2) Calculate the DFT of the image, namely F(u, v); (3) Multiply the filter function H(u, v) by F(u, v); (4) Calculate the IDFT of (3); (5) get the real part of (4); (6) use (-1) x+y Multiply the result in (5). in, ...

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 relates to a division method for an extracted watershed SAR image with a threshold method and marking, which combines an OTSU threshold method and watershed marking, and uses an image after threshold division as a source for marking a watershed mark, thereby effectively eliminating the influence of grain information and obtaining a new division method for the watershed SAR image based on threshold division. The method comprises the following steps: (1) Gaussian low-pass filtering is carried out for an original image Img to obtain an image GImg after filtering; (2) gradient is calucated for the image GImg after filtering to obtain an gradient image PGImg; (3) internal marker LImg of the original image Img is extracted with an Otsu method; (4) a classical watershed conversion is carried out for the internal marker to obtain an external maker WLImg; (5) the gradient image PGImg is modified with the internal marker and the external marker, and the forcement minimum technique is utilized for the modification so as to enable a local least area to only appear at a marking position; and (6) watershed conversion is carried out for the modified gradient image to obtain a final division image RImg. When the method is used for SAR image division, not only over-division can be reduced, but also the accuracy of the edge can be ensured.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a watershed SAR image segmentation method based on threshold value method mark extraction. It is used to suppress over-segmentation in synthetic aperture radar (SAR) image segmentation. Background technique [0002] Image segmentation is a very important step in image processing, which divides an image into subregions or objects with strong correlations. Image segmentation is usually used for further image analysis, recognition, compression coding, etc. The accuracy of segmentation directly affects the effectiveness of subsequent tasks. There are various image segmentation algorithms, among which threshold-based segmentation and region-based segmentation are widely used. The advantage of threshold-based segmentation is that the algorithm is simple, and closed and connected boundaries can always be used to define non-overlapping regions, but the disadvantage is that it ...

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): G06T7/00
Inventor 王爽焦李成张晓静侯彪刘芳钟桦缑水平
Owner XIDIAN 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