Image Segmentation via HSV Color Gamut Refinement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image segmentation methods based on edge detection or RGB color space are inadequate for accurately identifying different image regions, leading to low segmentation accuracy and poor three-dimensional imaging effects, especially in underwater sonar data where sea water, sea floor, and objects have distinct characteristics.
Innovation Solution
The method divides pixels into sets based on color gamut ranges and determines matching pixels using fuzzy sets and membership functions, refining the color gamut space to improve region recognition and segmentation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If edge detection method is used for image segmentation, then the segmentation process is simple, but the segmentation accuracy is low
Solution Approach 1:
The patent transforms the image from RGB color space to HSV color space, changing the parameter representation of colors. This allows for more intuitive and accurate color-based segmentation by separating hue, saturation, and value components, enabling better discrimination of different regions based on their color characteristics.
Solution Approach 2:
The patent divides the HSV color space into multiple color gamut ranges (red, green, blue, yellow, cyan, magenta regions) and creates separate binary images for each range. This segmentation of the color space allows independent processing and merging of different color regions, improving overall segmentation accuracy.
2Ease of operation
If RGB color space segmentation is used, then the implementation is straightforward, but the recognition of different image regions is inaccurate
Solution Approach 1:
The patent changes the color space parameters from RGB to HSV, where hue represents color type, saturation represents color purity, and value represents brightness. This parameter transformation enables more effective region recognition by allowing threshold-based segmentation on hue and saturation independently, which is more intuitive than RGB component analysis.
Solution Approach 2:
The patent introduces HSV color space as an intermediary between the original RGB image and the final segmented result. This intermediary representation facilitates better color-based discrimination by decoupling color information (hue) from intensity information (value), making the segmentation process more accurate while maintaining operational simplicity.
3Measurement precision
If color gamut space is refined by dividing into sub-cubes, then the segmentation accuracy improves, but the computational complexity increases
Solution Approach 1:
The patent divides the continuous HSV color space into six discrete color gamut ranges (red, green, blue, yellow, cyan, magenta) based on hue thresholds. This segmentation transforms a continuous parameter problem into a discrete classification problem, improving accuracy while keeping computational complexity manageable through simple threshold comparisons.
Solution Approach 2:
The patent processes only the hue and saturation components for color gamut classification, ignoring the value component during the primary segmentation. This partial action approach focuses computational effort on the most discriminative features for color-based segmentation, improving accuracy without unnecessarily increasing complexity across all three HSV components.
Data Source
AI summary
This disclosure relates to an image segmentation method and apparatus and image three-dimensional reconstruction method and apparatus, and to the field of computer technology. The segmentation method includes: dividing pixels in an image to be segmented among different pixel sets, according to color gamut ranges to which pixel values of the pixels belong; determining matching between pixels in each pixel set according to pixel values; and performing image segmentation on the image to be segmented according to the matching.