Grid Detection Method for Radiography Image Artifacts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for reducing X-ray scattering in radiography systems, such as anti-scatter grids, often introduce grid lines into images that can cause artifacts like Moiré patterns, which are difficult to remove and require time-consuming processing algorithms, necessitating a robust method for detecting grid presence and orientation in digital images.
Innovation Solution
A method involving the extraction of classification features from digital images, such as percentage of image regions perpendicular to the grid and power spectrum analysis, which are used in a classification algorithm like support vector machines to determine grid presence and orientation, allowing for efficient application of grid suppression algorithms only when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If anti-scatter grids are used to reduce X-ray scattering, then image quality is improved, but grid lines and Moiré artifacts are introduced into the image
Solution Approach 1:
The patent applies preliminary action by detecting the presence and characteristics of grids in the image before applying suppression algorithms. The system extracts classification features from the image, uses a trained classification algorithm to determine grid presence, and only then applies grid suppression processing. This preliminary detection step prevents unnecessary processing and ensures artifacts are removed only when grids are actually present.
2Object-generated harmful factors
If grid suppression algorithms are applied to remove grid lines, then artifacts are eliminated, but processing time increases significantly
Solution Approach 1:
The patent applies partial action by selectively applying grid suppression algorithms only to images where grids are detected. The system extracts features from the image, classifies whether a grid is present using a trained algorithm, and conditionally applies suppression processing only when needed. This approach processes only the necessary subset of images, significantly reducing overall processing time while maintaining artifact removal effectiveness.
3Object-generated harmful factors
If moving grids are used to remove grid lines, then artifacts are reduced, but system complexity and potential malfunctions increase
Solution Approach 1:
The patent replaces the mechanical moving grid system with a digital image processing solution. Instead of physically moving grids to eliminate artifacts, the system uses computational methods to detect grid presence in static images and apply digital suppression algorithms. This substitution eliminates mechanical complexity, removes dependencies on grid motion mechanisms, and provides a more reliable artifact removal approach.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This method effectively detects grid presence and orientation, enabling efficient removal of grid artifacts, reducing processing time and improving image quality by applying grid suppression algorithms only when grids are present, thus enhancing the robustness of image processing.
Implementation Method 1
Another example of a classification feature is the percentage of how many of these image regions have their maximum power spectrum magnitudes located around the same frequency
Data Source
AI summary
Method of detecting an image of a grid in a digital image by extracting a number of features from the digital image and classifying extracted features in a classification algorithm, preferably implemented with support vector machines, which is trained with the same training features extracted from a number of reference images.