Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Image filtering method

An image filtering and source image technology, applied in the field of image processing, can solve problems such as high algorithm complexity and resource occupation efficiency, and achieve the effects of wide application, improved accuracy rate, and reduced complexity and computing overhead

Inactive Publication Date: 2009-08-19
WUHAN FIRSTONG TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage is that when the template is large, the complexity of the algorithm is very high. A large number of matrix operations are involved in the convolution template traversal process, which takes up resources and is inefficient. It is difficult to apply it in applications with high real-time requirements such as video image recognition. Play a role

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 filtering method
  • Image filtering method
  • Image filtering method

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0039] Example 1, target shadow removal

[0040] In the video traffic information collection system, for the pictures obtained by the digital camera equipment, the purpose is to obtain the vehicle target. figure 2 Panel a in the figure is the target binary image with shaded outline after the moving target is extracted from the original color image, and panel b is the suspected shadow binary image obtained after the original color image is analyzed by shadow. The white pixels in the figure have a value of 1, and the black pixels have a value of 0. In order to ensure the acquisition of subsequent targets, it is necessary to remove the shadow contours that do not belong to the target car. Specific image filtering includes the following processes:

[0041] 1. For a certain pixel a of image a ij , the pixel will be further filtered only if the following conditions are met:

[0042] pixel a ij is a white spot;

[0043] Observation from image b with pixel a ij For the corresp...

example 2

[0050] Example 2, noise removal within the target

[0051] Still take the video traffic information collection system as an example. In the initially acquired binary image of the car target, such as image 3 As shown in image A in , there are irregular noise points, which should be removed.

[0052] 1. For a certain pixel a of image A ij , when a ij When it is a white point, the pixel is further filtered:

[0053] 2. Design template: take N as 11, 16 rays, and the number of pixels extracted by each ray is 4 (see figure 1 ).

[0054] 3. Design the function f of the first feature statistics: if the number of white points in the set A is greater than or equal to 2, then f=1, otherwise f=0. That is to say, if a set of pixel points A 1 , A 2 ,...,A 16 If more than half of the pixels in the set are white points, the feature of the set is regarded as a white point set.

[0055] 3. Design the function g of the second feature statistics: if the feature value f of a set of 16 ...

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 designs an image filtering method which designs a template of an odd-order square; the elements in the template are distributed radially; a pixel set is extracted according to radial lines for primary characteristic statistics; and then secondary characteristic statistics is carried out to the result of the primary characteristic statistics for the determination of the element characteristics in the template center. The method is used for image treatment based on grids, can realize the elimination of specific edge, the connection of discontinuous edges or the filling of specific area, thus having wide applications. The method can effectively reduce the complexity of later image segmentation process and the operation cost, and improve the accuracy of image segmentation.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image filtering method. Background technique [0002] Digital image processing for the purpose of target recognition, including processing processes based on raster images such as image filtering, edge enhancement, and moving object extraction in the early stage, and processing processes based on vector graphics such as region segmentation in the later stage . [0003] Compared with methods based on raster image processing, known region segmentation methods based on vector graphics have a large processing overhead, and there are very complicated search and judgment processes, which are not conducive to parallelization and streamlining of processing. To make image region segmentation simple and efficient, in the processing based on raster images, the edges of the region should be continuous and the noise in the region should be as little as possible. Know...

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): G06T5/00
Inventor 蔡东翔蔡雨轩陶冶
Owner WUHAN FIRSTONG TECH
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
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