An image splicing method for ultrasonic wide-view imaging

An image mosaic and image technology, applied in the field of image processing, can solve the problems that affect the stitching accuracy, require high operating techniques, reduce the number of matching points, etc., and achieve the effect of improving the overall quality, accurate basic transformation matrix, and accurate stitched images

Inactive Publication Date: 2019-04-16
沈阳聚声医疗系统有限公司
View PDF5 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In fact, due to the extrusion and angular rotation of the probe, the human tissue will be deformed, and the motion relationship between images is not simply expressed as translation and rotation. If rigid registration is used, the final stitching effect will be affected; there are also methods to improve Stitching speed, when determining the overlapping area, pre-divide the area to be registered, and save time by reducing the search range, but this method will reduce the number of matching points and affect the stitching accuracy
There are also methods to search for the matching area by controlling the moving speed of the probe, which requires higher operating techniques

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
  • An image splicing method for ultrasonic wide-view imaging
  • An image splicing method for ultrasonic wide-view imaging
  • An image splicing method for ultrasonic wide-view imaging

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] see figure 2 , is a schematic flowchart of an image mosaic method provided in Embodiment 1. The image stitching method includes the following steps.

[0056] S201: Acquire in real time two-dimensional B-mode images in which two consecutive adjacent frames of images have overlapping regions, the number of which is greater than 2 frames and has no upper limit.

[0057] The images to be spliced ​​may be multiple frames of images acquired and saved during the continuous scanning of the ultrasound probe, and there is an overlapping area between two adjacent frames of images. The total number of images to be spliced ​​is greater than 2 and there is no upper limit. The specific number can be set according to actual needs and system storage capacity, which is not limited in this embodiment.

[0058] It should be noted that the images to be stitched may be medical images or other types of images, which is not limited in this embodiment.

[0059] S202. Store the sequence imag...

Embodiment 2

[0079] see Figure 4 , is a schematic flowchart of an image mosaic method provided in the second embodiment. The image stitching method includes the following steps.

[0080] S401: Acquire a sequence of images to be stitched, where every two adjacent frames of the sequence of images to be stitched have overlapping regions.

[0081] It should be noted that this step S401 is the same as S201 in the above-mentioned first embodiment. For related introduction, please refer to the first embodiment, which will not be repeated here.

[0082] S402: On each acquired frame of image, respectively adopt a preset algorithm to extract target feature points. Specifically, the scale invariant feature transform (SIFT) algorithm is used to extract and represent features, see Figure 5 , using the SIFT algorithm to extract the feature points in the ultrasound image.

[0083] It should be noted that the feature extraction algorithm can also be other feature extraction algorithms, for example, it...

Embodiment 3

[0105] see Figure 9 , is a schematic flowchart of an image mosaic method provided in the third embodiment. The image stitching method includes the following steps.

[0106] The following steps S901-S907 are specific implementations of S208 in the first embodiment above.

[0107] S901: Using the image in the small-numbered data in two adjacent sets of data in the CPU memory image stitching module as a reference image, and the image in the large-numbered data as a floating image.

[0108] S902: The reference image is not moved, and the floating image is projected and transformed according to the basic transformation matrix in the small number data to the coordinate system where the reference image is located to obtain an overlapping area between the reference image and the floating image.

[0109] During each splicing process, the reference image is guaranteed not to move, and the floating image is projected and transformed into the coordinate system of the reference image ac...

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 splicing method, and the method comprises the steps: obtaining and storing sequence images to be spliced, and enabling every two adjacent frames of the sequence imagesto be spliced to have an overlapped region; Extracting feature points from each frame of image to be spliced, screening the extracted feature points through image gray correlation to obtain matchingpoint pairs, and calculating a basic transformation matrix between the two frames of images according to the registration point pairs of the two adjacent frames of images; And unifying every two adjacent frames of images in the to-be-spliced image to the same coordinate system according to the corresponding basic transformation matrix to complete image matching, splicing the two frames of images according to a preset algorithm, and carrying out image enhancement processing on the spliced part by using a detail enhancement algorithm at the same time. Therefore, an accurate basic transformationmatrix can be calculated through the screening method for the feature points through gray correlation, the image splicing quality is improved, and finally, the overall image quality is further improved through a rapid and efficient image detail enhancement processing method.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image stitching method for ultrasonic wide-view imaging. Background technique [0002] The medical ultrasound imaging system uses pulse-echo technology to detect the tissue structure, tissue characteristics and blood flow information inside the human body. Pulse echo is achieved using the probe of the ultrasound system. Due to the acoustic impedance characteristics of the probe, it needs to be in contact with the human body and needs a couplant, which limits the size of the probe and the contact surface of the human body, which also limits the imaging width and scanning angle of the probe, making the field of view of the generated image smaller. Displaying some areas of large organs cannot obtain the overall information of the organs in real time, which affects the doctor's overall understanding of the anatomical structure and its surrounding tissues, which brings gr...

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): G06T3/00G06T3/40A61B8/08
CPCG06T3/0068G06T3/4038A61B8/5246
Inventor 金程王丰
Owner 沈阳聚声医疗系统有限公司
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