Sparse-Sampling Image Reconstruction With Coordinate-Aware Artifact Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing observation systems face challenges in uniformly reducing artifacts in reconstructed images due to varying sampling coordinate groups, leading to inconsistent artifact reduction across different imaging methods.
Innovation Solution
An observation system that includes an imaging device and a processor subsystem, which sets a sparse sampling coordinate group, acquires pixel values, and uses a correction engine trained with specific data sets to generate a second reconstructed image, thereby uniformly reducing artifacts by learning from sampling coordinate groups, pixel value groups, and artifact-free or reduced-artifact images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If a correction engine trained with generic artifact reduction is used, then artifact reduction is achieved, but the reduction effect varies and is inconsistent across different imaging methods
Solution Approach 1:
The patent applies parameter changes by incorporating the sampling coordinate group as an additional input parameter to the correction engine. This allows the engine to adapt its artifact reduction process based on the specific sampling characteristics of different imaging methods, thereby achieving consistent artifact reduction across varying imaging conditions while maintaining broad applicability.
2Productivity
If sparse sampling is used to reduce measurement time, then productivity is improved, but artifacts occur in the reconstructed image
Solution Approach 1:
The patent converts the harmful effect of sparse sampling artifacts into a beneficial process by training the correction engine to specifically recognize and eliminate these artifacts. The engine learns from training data that includes sparse sampling patterns, enabling it to transform the degraded reconstructed images into high-quality images while maintaining the speed benefits of sparse sampling.
Solution Approach 2:
The correction engine acts as an intermediary between the sparse sampling process and the final reconstructed image. It receives the artifact-containing reconstructed image as input and outputs a corrected image, mediating the transformation from low-quality to high-quality images without affecting the original sparse sampling acquisition process.
3Measurement precision
If comprehensive training data including sampling coordinate groups is used, then artifact reduction accuracy is improved, but data processing complexity increases
Solution Approach 1:
The patent segments the training data into distinct components: sampling coordinate groups, pixel value groups, and reference images. This segmentation allows the system to process and utilize each type of data independently and efficiently, managing the complexity of comprehensive training data while achieving high artifact reduction accuracy through the integrated use of all segments.
Data Source
AI summary
Provided is technology capable of uniformly reducing artifacts that are in a reconstructed image and that change due to a sampling coordinate group. This observation system comprises an image capture device and a processor subsystem. The processor subsystem sets a sparse sampling coordinate group for a sample, acquires a pixel value group corresponding to the sampling coordinate group on the sample, and gives, to a correction engine, the pixel value group or a first reconstructed image that has been generated on the basis of the pixel value group, so that a second reconstructed image is generated.The correction engine is trained using the following data (1) to (3) pertaining to the sample or a training sample:(1) the sampling coordinate group;(2) the pixel value group or a reconstructed image which has artifacts and which has been reconstructed from the pixel value group using the sampling coordinate group; and(3) an image which contains no artifacts or in which artifacts are reduced.