Two-dimensional plane representation method for images of alimentary tract

A two-dimensional plane, digestive tract technology, applied in image data processing, 2D image generation, instruments, etc., can solve problems such as limited effect, splicing effect, and no solution to the impact of the shooting angle of the intestinal cavity, so as to facilitate the understanding of the image , The effect of improving the efficiency of reading pictures and reducing the difficulty of work

Inactive Publication Date: 2012-05-02
TSINGHUA UNIV
View PDF6 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But the model is based on detection of capsule endoscope motion, which can only track the smooth motion of the capsule forward or backward, and when it moves sideways or flips over, the resulting mosaic is not an accurate representation of the GI tract. Description, and due to the angle of view of the capsule, the cavity of the intestine has an impact on the stitching of the images, making the final stitching renderings unsatisfactory, although it is mentioned in the article that the expanded images generated by the model can reduce the time for doctors to diagnose , but the effect is limited. In f

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
  • Two-dimensional plane representation method for images of alimentary tract
  • Two-dimensional plane representation method for images of alimentary tract
  • Two-dimensional plane representation method for images of alimentary tract

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] This embodiment provides a feasible method for forming a two-dimensional plane representation of an intestinal image, and the method flow is as follows figure 2 shown.

[0067] Classify the read images, that is, divide the images into turbid images and non-turbid images. The turbid images are those images whose intestinal wall information is covered by food residues and turbid liquid in the intestine. The purpose of image classification is to remove these Part of the image, because the cloudy image is not helpful for doctors to diagnose.

[0068] The classification can adopt the feature-based pattern classification method, and the method flow is as follows:

[0069] (1) Extract the color histogram of the read image.

[0070] (2) For the RGB three channels of the read image, each channel adopts 8 bins, and an 8 bin of each image is obtained 3 dimension vector as its feature vector.

[0071] (3) Using a support vector machine (SVM) method to train the feature vectors...

Embodiment 2

[0125] An embodiment of the present invention provides a feasible method for forming a two-dimensional plane representation of an intestinal image, and the scheme flow is as follows Figure 7 shown.

[0126] The process of this embodiment is basically the same as that of Embodiment 1, that is, a large number of images can be divided into several subsets according to the attitude information attached to each captured image, and then each image of each subset can be processed sequentially and finally merged. The difference is that the method adopted in this embodiment after obtaining the image subset is to map the image, and the method of mapping adopts the method of grid division, and the process is as follows:

[0127] (1) Determine the geometric dimensions of the two-dimensional plane representation: determine the final two-dimensional plane representation based on information such as the angle of view of the camera in the wireless balloon endoscope, the image resolution, the...

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 a two-dimensional plane representation method for the images of the intestinal tract. The realization of the method is based on a wireless sacculus endoscope system in which an attitude motion sensing module and an intestinal cavity identifying module are embedded. The method comprises several following steps: reading images; classifying an image set into turbid images and non-turbid images; dividing a non-turbid image set into a plurality of subsets; calculating the relative position relationship of a camera and the wall of the intestinal tract when shooting each image; carrying out the treatment of rectifying or mapping on the images; carrying out registered splicing or similar matching on the images after being rectified or mapped; and combining the subsets to form a two-dimensional expansion drawing of the wall of the intestinal tract. By adopting the two-dimensional representation method for the images of the intestinal tract, which is provided by the invention, the redundant contents of images collected by a wireless endoscope can be greatly reduced. The two-dimensional plane representation method for the images of the intestinal tract is beneficial for a doctor to comprehend the images, the working difficulty of the doctor can be lowered, and the film reading efficiency is enhanced.

Description

technical field [0001] The invention relates to the technical field of auxiliary equipment for clinical observation and diagnosis of intestinal diseases, in particular to a two-dimensional representation method of digestive tract images. Background technique [0002] In the past ten years, with the rapid development of microelectronics, micromechanics, information processing, wireless communication and other technologies, the development of medical endoscope technology has been greatly promoted. Represented by the Wireless Capsule Endoscopy system (Wireless Capsule Endoscopy), the inspection of the human digestive tract, especially the small intestinal cavity, can be completed by the subject swallowing a capsule with a built-in wireless function micro-camera. The unique advantage of this technology is that it not only achieves painless diagnosis, but also breaks through the limitation that conventional endoscopes cannot directly inspect the small intestine. Currently, it is...

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
IPC IPC(8): G06T11/00
Inventor 王丹谢翔李国林谷荧柯孙天佳胡军王志华
Owner TSINGHUA UNIV
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