Unlock instant, AI-driven research and patent intelligence for your innovation.

Image contour automatic extraction method and system

An automatic extraction and image contour technology, applied in the field of image processing, can solve the problems of long time-consuming automatic delineation, large amount of registration calculation, poor registration accuracy, etc., and achieve the effect of smooth image contour, increased recognition efficiency, and convenient extraction

Active Publication Date: 2017-06-20
SHENZHEN YINO INTELLIGENCE TECH
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantages of this method are: it is necessary to prepare a suitable prior data set in the early stage, and the registration accuracy is not good, the registration calculation is large, and the automatic sketching takes a long time

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 contour automatic extraction method and system
  • Image contour automatic extraction method and system
  • Image contour automatic extraction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0088] Please refer to figure 1 , Embodiment 1 of the present invention is: an image contour automatic extraction method, which can be applied to medical images, and has high recognition efficiency and good accuracy when performing image contour extraction. Including the following steps:

[0089] S1. Preset a seed point of a two-dimensional tomographic image, and acquire a target image area of ​​the one-dimensional tomographic image according to the seed point. Further, the target image area can be acquired with the seed point as the center, and the seed point can be any point of each layer in the two-dimensional tomographic image, which is mainly selected according to the area to be extracted; the size of the target image area can be The shape of the target image area can be a regular circle or square, or other irregular shapes, depending on the needs and the properties of the two-dimensional tomographic image.

[0090] S2. Perform the first region growing on the target ima...

Embodiment 2

[0098] Please refer to figure 2 , Embodiment 2 of the present invention is a further extension of Embodiment 1 above, and the similarities will not be described again. The difference is that step S2 specifically includes:

[0099] judging whether the pixel value of a pixel in the target image area is within a preset pixel threshold range;

[0100] If so, reset the pixel value of the one pixel point to 255;

[0101] If not, reset the pixel value of the one pixel point to 0.

[0102] In this embodiment, each pixel of the target image area is judged one by one, so as to obtain an effective target image area and prepare for the second region growing.

[0103] Step S3 specifically includes:

[0104] Take the pixel point with a pixel value of 255 on the binary image as the center of the circle, and make a circle with a preset radius, and the preset radius can be set according to needs;

[0105] Determine whether the pixel values ​​of the rest of the pixels in the circle are 255...

Embodiment 3

[0114] Please refer to figure 2 , Embodiment 3 of the present invention is a specific application scenario of the above-mentioned embodiment, specifically taking the contour extraction of a spinal cord tomographic image in a medical image as an example for illustration, which can quickly and accurately perform contour extraction on a two-dimensional tomographic spinal cord image in three dimensions Automatic extraction.

[0115] First select a seed point, obtain the target image area of ​​the two-dimensional tomographic image according to the seed point, when performing spinal cord contour extraction, a side length of 40 / pixel spacing can be cut on the two-dimensional tomographic image where the seed point is located (that is, 40 divided by the pixel pitch) is a square area, of course, it can also be an area of ​​other shapes.

[0116]A pixel threshold range is preset, and then a first region growing is performed on the target image region according to the preset pixel thres...

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 an image contour automatic extraction method and system. The method includes the following steps: presetting a two-dimensional tomographic image seed point, and obtaining a target image area of a tomographic image; conducting first region growing on the target image area according to a preset image threshold range, and obtaining a binary image; conducting second region growing on the binary image; conducting expansion on the binary image that has undergone the second region growing, and extracting the contour of the binary image after expansion; calculating the center of gravity of the contour, and taking the center of gravity as a seed point of an adjacent image layer; and obtaining a target image area of the adjacent image layer on the basis of the seed point of the adjacent image layer. The image contour automatic extraction method and system can quickly and accurately extract a two-dimensional tomographic image in an automatic manner, and are especially suitable for medical tomographic images such as extraction of spinal cord contours.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image contour automatic extraction method and system. Background technique [0002] In tomographic images such as CT and MR, a single organ or target region consists of a set of contour lines distributed on multiple two-dimensional tomographic images. In order to ensure precision and accuracy, most radiologists or other well-trained medical staff manually draw the contour lines on each two-dimensional tomographic image in clinical practice. This manual drawing operation is cumbersome and greatly wastes the time of medical staff. and energy, and may even make mistakes due to personnel fatigue. [0003] At present, there are also some methods for automatically delineating contour lines, such as methods based on grayscale and gradient information, among which the region growing method is more representative. This type of method has a high delineation speed, but is sensi...

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): G06T7/13G06T7/155G06T7/66
CPCG06T2207/10081G06T2207/10088G06T2207/20036G06T2207/20156
Inventor 曲宝林蔡博宁戴相昆徐寿平杨涛马娜黄玉荣冯林春马林陈子杰
Owner SHENZHEN YINO INTELLIGENCE TECH