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

Image feature point detection method

A detection method and image technology, applied in the field of image processing, can solve the problems of wrong matching point pairs, slow detection speed, high complexity of detection algorithm, etc., and achieve the effect of stabilizing feature points, increasing speed, and low detection complexity

Active Publication Date: 2017-03-15
SHANGHAI UNITED IMAGING HEALTHCARE
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when using the existing feature-based image stitching method to stitch X-ray images, when detecting the feature points in the image to be stitched, the complexity of the detection algorithm is high and the detection speed is slow.
In addition, when using the existing image stitching method based on feature points to achieve image stitching, there are still wrong matching point pairs in the matching point pairs, and the accuracy of the matching point pairs is low, which leads to the failure of image stitching when using the feature-based image stitching method. , the splicing accuracy of the images obtained by splicing is not high, which has a certain impact on clinical diagnosis

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 feature point detection method
  • Image feature point detection method
  • Image feature point detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] See figure 1 , figure 1 It is a schematic flow diagram of a method for detecting feature points in an image according to Embodiment 1 of the present invention; figure 1 As shown, the detection method of the feature point in the image of the present embodiment comprises:

[0047] S101: Perform pyramid decomposition on the image, and construct a differential pyramid image based on the decomposed image;

[0048] S102: traverse each layer of the differential pyramid image, and search for an extreme point in each layer of the differential pyramid image, the extreme point is associated with the absolute value of the gray value of the pixel in the preset neighborhood;

[0049] S103: Remove pixels on the strong edge of the image among the extreme points to obtain feature points in the image.

[0050] Execute S101 to perform pyramid decomposition on the image. In this embodiment, Gaussian pyramid decomposition is performed on the image, or a Gaussian pyramid of the image is e...

Embodiment 2

[0081] This embodiment provides a method for determining matching point pairs, please refer to figure 2 , figure 2 is a schematic flowchart of a method for determining matching point pairs in Embodiment 2 of the present invention, as figure 2 As shown, the method for determining the matching point pair includes:

[0082] S101': Perform pyramid decomposition on the first image and the second image, and respectively construct a first differential pyramid image corresponding to the first image and a pyramid image corresponding to the second image based on the decomposed first image and the second image a second differential pyramid image; the first image and the second image are adjacent images;

[0083] S102': traverse each layer of the first differential pyramid image, search for extreme points in the differential pyramid image of each layer, traverse each layer of the second differential pyramid image, and search for extreme points in the differential pyramid image of eac...

Embodiment 3

[0138] This embodiment provides a method for determining matching point pairs. The difference from Embodiment 2 is that the method for removing wrong matching point pairs in the initial matching point pairs in this embodiment is different from that in Embodiment 2. Please refer to Figure 4 , Figure 4 It is a schematic flow chart of the method for determining a matching point pair in Embodiment 3 of the present invention; in this embodiment, the method for determining a matching point pair includes:

[0139] S101': Perform pyramid decomposition on the first image and the second image, and respectively construct a first differential pyramid image corresponding to the first image and a pyramid image corresponding to the second image based on the decomposed first image and the second image a second differential pyramid image; the first image and the second image are adjacent images;

[0140] S102': traverse each layer of the first differential pyramid image, search for extreme ...

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 an image feature point detection method. The image feature point detection method comprises the following steps: carrying out pyramid decomposition on an image, and constructing a difference pyramid image based on decomposed images; traversing each layer of the difference pyramid image and searching an extreme point of each layer of difference pyramid image, wherein the extreme point is associated with an absolute value of a gray value of a pixel point in a preset neighbor region; and removing pixel points on a strong edge of the image in the extreme point to obtain feature points in the image. According to the technical scheme, the image feature point detection method is low in complexity and fast in speed; and the obtained feature points are stable.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method and device for detecting feature points in an image, a method and device for determining matching point pairs, an image acquisition method and device, and an X-ray photography system. Background technique [0002] Digital Radiography (DR, Digital Radiography) equipment is an advanced medical equipment formed by the combination of computer digital image processing technology and X-ray radiation technology. Digital X-ray imaging equipment is widely used because of its low radiation dose, high image quality, high disease detection rate and diagnostic accuracy. [0003] When diagnosing orthopedic diseases such as spondylolisthesis, scoliosis, and lower limb deformities, or performing fracture reduction, joint displacement, osteotomy, and pedicle screw insertion, the assistance of medical imaging equipment is needed, and X-ray imaging equipment is due to its ...

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): G06T7/00G06T7/33G06K9/46
CPCG06T3/4038G06T7/0012G06T2207/20016G06T2207/10116G06T2207/30008G06T2207/20221G06V10/462G06V2201/033
Inventor 胡扬牛杰徐亮王汉禹
Owner SHANGHAI UNITED IMAGING HEALTHCARE