Method for detecting and extracting correlation pixels in image and application thereof

A technology in pixels and images, applied in image analysis, image data processing, instruments, etc.

Inactive Publication Date: 2011-01-26
HUAZHONG UNIV OF SCI & TECH
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] (2) There is still room to ...

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
  • Method for detecting and extracting correlation pixels in image and application thereof
  • Method for detecting and extracting correlation pixels in image and application thereof
  • Method for detecting and extracting correlation pixels in image and application thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] Below in conjunction with accompanying drawing and example the present invention is described in further detail.

[0048] A method for detecting and extracting image-associated pixels described in the present invention is carried out according to the following steps:

[0049] The image used in this embodiment is a binary image, the foreground pixel is assumed to be 1, and the background pixel is assumed to be 0.

[0050] (1) Take out a pixel point located in the same column from two adjacent pixel rows of the image;

[0051] (2) If both pixels are 0, do nothing. Return to step 1. If these two pixels are not all 0, then the global coordinate G(Pi) that is not currently 0 pixel point is assigned to the pixel value, that is, Pi(xi, yi)=G(Pi)=y*N+x if two If none of the pixels is 0, the above operation is only performed on the pixels of odd rows.

[0052] (3) Continue to take out the next group of pixels. If the two pixels are not all 0, then assign the value assigned l...

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 method for detecting and extracting correlation pixel points in an image, which is used for extracting and expressing a local connected domain consisting of continuous foreground points among a plurality of pixel rows of the image. The invention also discloses a method for labeling the image based on the detection and extraction method, which is divided into three stages, namely, a stripe extracting and expressing stage, a strip merging stage, and a tagged value assignment stage, wherein the local connected domain consisting of the continuous foreground points between two adjacent pixel rows of the image is defined to be the stripe, and the local connected domain consisting of the continuous foreground points in a row is defined to be a segment. The method improves the detection efficiency of the correlation pixel points, overcomes the defect of higher additional memory cost by the existing labeling method, and further improves the speed of the labeling method so as to complete the high-speed and strict image data labeling work.

Description

technical field [0001] The invention belongs to the field of image processing and pattern recognition, and in particular relates to a method for detecting and extracting associated pixel points in an image and a fast marking method without additional memory overhead based on the method. Background technique [0002] As we all know, image marking technology is one of the most basic technologies in the field of image processing and pattern recognition. This technology exists in almost all image processing, especially in the application of pattern recognition, such as the extraction of regions of interest in radar and remote sensing images; the high-level management of target information in automatic target recognition equipment such as missiles, drones, and self-driving cars. Extraction; extraction of specific tissue regions in medical images; target recognition and tracking in monitoring equipment; text recognition for book digitization; fingerprint recognition, etc. The lab...

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): G06T7/00
Inventor 赵华龙范晔斌
Owner HUAZHONG UNIV OF SCI & 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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap