Intraoral Scanner Surface Differentiation for Accurate 3D Stitching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Intraoral 3D scanners face challenges in accurately stitching together views due to deformable or moving surfaces within the oral cavity, leading to inaccuracies in the combined 3D topography measurement, as existing methods require additional data or are computationally expensive.
Innovation Solution
A method using a score-finding algorithm, potentially machine learning-based, to determine the type of surface and assign weights for weighted stitching, considering surface geometry and neighborhood information, to generate a digital 3D representation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional stitching algorithms are used that assume rigid surfaces, then the stitching process is computationally efficient and simple to implement, but the measurement precision deteriorates when deformable surfaces are present
Solution Approach 1:
The patent applies local quality by differentiating between various surface types (teeth, gingiva, tongue, cheeks, foreign objects) and applying different stitching strategies to each. The system analyzes local surface characteristics such as geometry, color, and texture to identify surface type, then assigns appropriate weights and stitching methods to each surface type individually rather than using a uniform approach for all surfaces.
Solution Approach 2:
The patent changes parameters by introducing surface type classification based on multiple parameters including geometry, color, and texture characteristics. The system dynamically adjusts stitching weights and algorithms based on the identified surface type, transforming the static rigid-surface assumption into a dynamic multi-parameter-based stitching approach that adapts to different oral cavity surfaces.
2Measurement precision
If non-rigid stitching algorithms are used to handle deformable surfaces, then the measurement precision improves, but the computational cost and processing time increase significantly
Solution Approach 1:
The patent applies local quality by differentiating between various surface types (teeth, gingiva, tongue, cheeks, foreign objects) and applying different stitching strategies to each. The system analyzes local surface characteristics such as geometry, color, and texture to identify surface type, then assigns appropriate weights and stitching methods to each surface type individually rather than using a uniform approach for all surfaces.
Solution Approach 2:
The patent applies partial action by selectively applying complex non-rigid stitching algorithms only to specific surface types where they are most beneficial, while using simpler rigid-surface stitching for other areas. The surface type classification enables the system to apply computational resources partially and selectively rather than uniformly across all surfaces, reducing overall computational burden while maintaining accuracy where needed.
3Ease of operation
If color-based surface classification is used to identify teeth for stitching, then the ease of operation improves, but the measurement precision deteriorates due to color variability and discoloration
Solution Approach 1:
The patent merges multiple surface classification approaches by combining color-based classification with geometry-based and texture-based classification methods. The system integrates these different classification strategies to compensate for the limitations of each individual method, creating a more robust and accurate surface type identification system that overcomes color variability and discoloration issues.
Solution Approach 2:
The patent introduces geometry and texture characteristics as intermediary parameters that mediate between the simple color-based classification and the final surface type identification. These intermediary parameters provide additional discriminatory power and help resolve ambiguities that arise from color alone, such as distinguishing discolored teeth from actual non-tooth surfaces.
4Measurement precision
If all recorded views are stitched together uniformly, then the productivity is high and processing is simple, but the measurement precision deteriorates due to inclusion of deformable surfaces
Solution Approach 1:
The patent applies local quality by differentiating between various surface types (teeth, gingiva, tongue, cheeks, foreign objects) and applying different stitching strategies to each. The system analyzes local surface characteristics such as geometry, color, and texture to identify surface type, then assigns appropriate weights and stitching methods to each surface type individually rather than using a uniform approach for all surfaces.
Solution Approach 2:
The patent applies partial action by selectively applying complex non-rigid stitching algorithms only to specific surface types where they are most beneficial, while using simpler rigid-surface stitching for other areas. The surface type classification enables the system to apply computational resources partially and selectively rather than uniformly across all surfaces, reducing overall computational burden while maintaining accuracy where needed.
Data Source
AI summary
A method for generating a digital 3D representation of at least a part of an intraoral cavity, the method including recording a plurality of views containing surface data representing at least the geometry of surface points of the part of the intraoral cavity using an intraoral scanner; determining a weight for each surface point at least partly based on scores that are measures of belief of that surface point representing a particular type of surface; executing a stitching algorithm that performs weighted stitching of the surface points in said plurality of views to generate the digital 3D representation based on the determined weights; wherein the scores for the surface points are found by at least one score-finding algorithm that takes as input at least the geometry part of the surface data for that surface point and surface data for points in a neighbourhood of that surface point.