Supercharge Your Innovation With Domain-Expert AI Agents!

Central projection based image form characteristic line extracting method

A technology of central projection and image morphology, applied in image analysis, image data processing, instruments, etc., can solve the problem that automatic identification technology cannot obtain real application, automatic identification technology lags behind, and lacks effective representation of cell morphology and texture etc. to achieve the effect of reducing subjective interference, reducing the burden and the influence of human factors, and improving the accuracy of interpretation

Inactive Publication Date: 2008-09-17
SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Unfortunately, at present, due to the lag of the corresponding automatic recognition technology, the automatic recognition technology, especially the automatic recognition technology of cell shape and texture, cannot be really applied. The key is the lack of effective features representing cell shape and texture.

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
  • Central projection based image form characteristic line extracting method
  • Central projection based image form characteristic line extracting method
  • Central projection based image form characteristic line extracting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] refer to figure 1 , the central projection-based image morphological feature line extraction method includes the following steps:

[0024] a. Collect image S1 through a microscope;

[0025] b. Binarize the collected image into a binary image, and segment the target image S3 from the binary image;

[0026] c. Calculate the center of mass S4 of the target image, set the central projection angle θ, θ should be an integer factor of 360°; take the center of mass as the starting point, and the angle along the reference line is 0, θ, 2θ, ... , (N-1) the direction of θ respectively make rays, wherein N=360° / θ, record the number P of pixels of each ray passing through the target image θ (n), where 0≤nθ (n) Normalization, sort the normalized values ​​from small to large to form a new sequence q θ (m), where 0≤mθ (m)), thereby forming the feature line S7 of the target image.

[0027] The collected grayscale image can be converted into a binary image by using the threshold meth...

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 present invention includes 1, collecting picture; 2, making binarization to collected picture and partition out target image; 3, calculating said target image centroid, configuring central projection angle theta; using said centroid as starting point, along included angle direction with reference line respectively doing ray, recording each ray through said target image pixel number p theta (n) (0 <= n < n), making all nonzero P theta (n) normalization, sorting to form new sequence q theta m), in coordinate system in turn connecting whole point (m , q theta (m)), forming target image characteristic line. Said method can automatically partition out whole target image from collected picture and automatically extract target image characteristic line, and capable of being widely used in biology, pathology, pharmaceutical chemistry, genetic gene, and clinical diagnosis etc field.

Description

technical field [0001] The invention relates to the field of representation and extraction of various image morphological features in image processing, in particular to an image morphological feature line extraction method based on central projection. Background technique [0002] At present, the morphological analysis of the target image in the image has been widely used, especially the cell morphological analysis under the microscope has been widely used in biology, agronomy, medicine, pharmacy, animal science, environmental resources, materials, chemical industry and other fields. Various processing and morphological automatic analysis can be performed on the microscopic images of light microscope and electron microscope, such as tissue cell morphology analysis, metal microstructure and grain size analysis, pollutant content analysis in oil, agricultural seed morphology analysis, various Measurement of geometric dimensions of tiny special-shaped parts, morphology analysis...

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): G06K9/60G06K9/46G06T7/60
Inventor 袁克虹程乾生
Owner SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com