Method for extracting image shape characteristics

A technology of shape features and extraction methods, applied in image analysis, image data processing, instruments, etc., can solve single problems

Inactive Publication Date: 2010-09-22
HUAZHONG UNIV OF SCI & TECH
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014] Including area, perimeter, length, width, perimeter square to area ratio, the square to area ratio of the average distance from all points to the boundary, regional moment invariance, and polygon fitting, etc. These shape parameters are simple and easy to program. However, Too simple to complete the precise classification and analysis of nuclei with different shapes

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 extracting image shape characteristics
  • Method for extracting image shape characteristics
  • Method for extracting image shape characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0064] The biggest advantage of the chamfering distance transformation is that the distance information can be obtained by performing two serial scanning processes, the calculation amount is small, and more accurate segmentation results can be obtained. In fact, in the measurement and judgment of shape, the distance from the point to the edge is also a very important index. Therefore, we introduce the chamfer distance transformation to measure the shape.

[0065] The original distance transformation only obtains distance information but not direction information, and direction information is also very important when performing shape recognition. Therefore, in the two scans of the distance transformation, we record the direction information as well as the distance information for later judgments.

[0066] An image shape feature extraction metho...

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 distance conversion-based shape characteristic description method. The method comprises the following steps of: performing distance conversion on an image, and recording a distance value of each point and corresponding vector information; and then calculating shape characteristic parameters such as integral length, integral acute angle, integral obtuse angle, edge length, edge acute angle, edge obtuse angle and the like by using a half of the maximum distance value as a threshold value according to the method provided by the invention. The shape characteristic parameters can reflect the characteristics of a shape on different scales and provide more detailed information for identification of cell nucleuses so that the method has good separable property on white cells with different nuclear shapes.

Description

technical field [0001] The invention relates to an image shape feature extraction method, which is applied to extract blood cell nucleus shape feature parameters. Background technique [0002] Due to the large number of cell types, some of which have subtle differences, the selection and determination of shape parameters also put forward higher requirements. There have been some researches on the shape feature vector extraction of blood cells at home and abroad, and the shape parameter extraction methods currently used mainly include the following: [0003] 1. Method for extracting circular deviation based on circle or ellipse fitting error [0004] Such methods mainly include: the minimum area circle method, the least square circle method, the minimum circumscribed circle method and the maximum inscribed circle method. The roundness error value evaluated by the minimum area circle evaluation criterion is the smallest and unique; The roundness error value evaluated by the ...

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): G06K9/46G06T7/00G06K9/62
Inventor 汪国有林晨郑馨李一安朱曼瑜刘建国
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