Image Splicing via Feature Point Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional image splicing methods for medical imaging, such as digital radiography, are complex and inefficient, often resulting in inaccurate point pairs that affect the accuracy of image splicing and clinical diagnosis.
Innovation Solution
A system and method that acquire and process images by determining feature points, matching point pairs, and adjusting image regions to generate a spliced image, using techniques like Gaussian pyramid decomposition and histogram analysis to improve the accuracy of image overlap and alignment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional splicing methods are used, then image splicing can be performed, but the complexity of detecting feature points increases and efficiency decreases
Solution Approach 1:
The patent segments the image splicing process into distinct modules: feature point detection, point pair matching, and splicing execution. By dividing the complex task into manageable segments with specialized algorithms for each stage, the system reduces overall complexity while improving efficiency through optimized individual components
Solution Approach 2:
The patent introduces point pairs as an intermediary element between feature point detection and final image splicing. These point pairs serve as matching indicators that bridge the detection phase and the splicing phase, enabling more efficient processing by pre-identifying correspondences before actual splicing occurs
2Measurement precision
If conventional splicing methods are used, then feature points can be detected, but the accuracy of matched point pairs decreases
Solution Approach 1:
The patent implements feedback mechanisms where the splicing results are evaluated and used to refine point pair matching. The system continuously adjusts matching criteria based on splicing quality metrics, ensuring that only high-accuracy point pairs are used for final splicing, thereby improving both measurement precision and reliability
Solution Approach 2:
The patent dynamically adjusts matching parameters such as threshold values and similarity criteria based on image characteristics and splicing requirements. By changing parameters adaptively rather than using fixed conventional thresholds, the system achieves higher accuracy in point pair matching and more reliable splicing results
Data Source
AI summary
The present disclosure relates to systems and methods for image splicing. The systems and methods may acquire a first image and a second image, determine a plurality of first feature points in a first region of the first image, determine a plurality of second feature points in a second region of the second image, then match the plurality of first feature points with the plurality of second feature points to generate a plurality of point pairs. Based on the plurality of point pairs, a third region on the first image and a fourth region on the second image may be determined. Finally, a third image may be generated based on the first image and the second image, wherein the third region of the first image may overlap with the fourth region of the second image in the third image.