Interval search type geometric parameter self-calibration method based on artifact evaluation
A geometric parameter and search-based technology, applied in image data processing, projection reproduction, 2D image generation, etc., can solve the problem of low accuracy of criterion correction, improve the effect of classification evaluation, save search time, and reduce iterative search range effect
Pending Publication Date: 2022-01-04
PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The present invention aims at the problem of low accuracy of criterion correction existing in the existing geometric parameter self-calibration method, and proposes an interval search type geometric parameter self-calibration method based on artifact evaluation
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0042] The present invention will be further explained below in conjunction with accompanying drawing and specific embodiment:
[0043] Such as figure 1 As shown, a self-calibration method of geometric parameters based on interval search based on artifact evaluation includes:
[0044] Step S101: Estimate initial values of geometric parameters to be calibrated using projection and alignment methods; specifically, initial values of geometric parameters to be calibrated are used for 3D reconstruction of projection data.
[0045] Specifically, in the self-calibration method, a relatively accurate initial value can effectively reduce the search range. In this embodiment, the initial value u of the geometric parameter to be calibrated is solved by using projection and its method 0. For the fan-beam CT system, an array detector is used, and the acquired projected image of the detected object is data composed of multiple one-dimensional vectors. When the detected object is sca...
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
Login to View More Abstract
The invention discloses an interval search type geometric parameter self-calibration method based on artifact evaluation. The method comprises the following steps: 1, estimating an initial value of a geometric parameter to be calibrated by using a projection and alignment method; 2, performing projection data three-dimensional reconstruction based on the initial values of the geometric parameters to be calibrated to obtain three-dimensional body data; slicing the reconstructed three-dimensional body data to obtain a reconstructed image based on an estimated value; 3, constructing a geometric artifact evaluation network; 4, performing geometric artifact level evaluation on the reconstructed image based on the estimated value by using a geometric artifact evaluation network, and setting a parameter search step size and a search interval according to the geometric artifact degree; and when the geometric artifact evaluation network determines that the reconstructed image has no geometric artifact in the search interval and the parameter search reaches global optimum, completing geometric parameter calibration. According to the invention, the geometric artifact evaluation network can be utilized to quickly and accurately complete the self-calibration of the geometric parameters.
Description
technical field [0001] The invention belongs to the technical field of CT image processing, in particular to an interval search type geometric parameter self-calibration method based on artifact evaluation. Background technique [0002] The mismatch of geometric parameters of the CT system leads to geometric artifacts in the reconstructed image, which seriously affects the acquisition of image information. The geometric parameter self-calibration method uses the characteristics of the collected projection data or the characteristic information of the reconstructed image as a criterion to iteratively solve the geometric parameters of the system, complete the correction of geometric artifacts, and improve the image quality. The low accuracy of criterion correction is the biggest deficiency of existing geometric parameter self-calibration methods. The residual network in deep learning is widely used in the field of image processing. It recognizes the structural features in 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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T11/00G06T17/00G06N3/04
CPCG06T11/008G06T17/00G06N3/048G06N3/045
Inventor 李磊朱明婉韩玉闫镔席晓琦朱林林孙艳敏谭思宇
Owner PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU