Endoscope image reflection point recognition method, device, equipment and storage medium
CN120070995BActive Publication Date: 2026-07-21THE AFFILIATED HOSPITAL OF XUZHOU MEDICAL UNIV
View PDF 2 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- THE AFFILIATED HOSPITAL OF XUZHOU MEDICAL UNIV
- Filing Date
- 2025-02-12
- Publication Date
- 2026-07-21
AI Technical Summary
Technical Problem
In the existing technology, the methods for identifying reflective points and actual white points cannot effectively distinguish between them, leading to misprocessing and affecting the examination or treatment effect.
Method used
By acquiring the original endoscopic image, performing grayscale processing and image segmentation, converting it to the HSB color space, dividing the region of interest, calculating reflectivity performance parameters and weights, determining the probability of reflective points, and avoiding misidentification of actual white points.
Benefits of technology
Accurately identify reflective points, avoid misinterpreting actual white spots, ensure endoscopic image quality, and guarantee the accuracy of examinations or treatments.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN120070995B_ABST
Abstract
The present application relates to the technical field of computer vision, and provides a kind of endoscope image reflection point identification method, device, equipment and storage medium for accurately identifying reflection point in endoscope image, the method comprises the following steps: by image segmentation, the region of interest is segmented out, and the region of interest is divided into multiple pixel sets of interest according to the gradient information of the region of interest, and multiple comparison sets corresponding to each pixel set of interest are obtained;For each pixel set of interest, calculate the reflection performance parameter and the reflection performance weight of each comparison set corresponding to the pixel set of interest;According to the reflection performance parameter and the reflection performance weight of each comparison set corresponding to the pixel set of interest, calculate the probability parameter that the pixel set of interest is the pixel set in reflection point, and calculate the probability parameter that the region of interest is reflection point;According to the probability parameter that the region of interest is reflection point, judge whether the region of interest is reflection point.
Need to check novelty before this filing date? Find Prior Art