Intraoral 3D Image Stitching via Temporal Reference Correction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Intraoral scanners generate three-dimensional images with inaccurate deformations due to rapid movement and hand tremors, leading to subpar image quality from stitched two-dimensional images.

Innovation Solution

A three-dimensional image generation method that projects and captures multiple light patterns at different times, allowing for the generation of additional images based on existing ones to reduce discrepancies and enhance image stitching, thereby improving the quality of the final three-dimensional image.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the scanner is moved swiftly to capture multiple images, then the productivity is improved, but the measurement precision deteriorates due to inaccurate deformations

Engineering Contradiction:

Improveimage capture speedVSAvoidthree-dimensional image accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent applies preliminary action by capturing a reference image before the actual measurement sequence. This reference image serves as a baseline to compensate for movements and deformations that occur during rapid scanning, allowing the system to maintain measurement precision even when the scanner moves swiftly to capture multiple images.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements feedback by using the reference image to correct and adjust the subsequent captured images. The system compares the reference image with the captured images and applies correction algorithms to compensate for movements and deformations, thereby maintaining measurement precision while allowing high-speed capture.

Inventive Principle:

Principle #23Feedback

2Ease of operation

If the user's hand exhibits tremors during scanning, then the ease of operation is maintained, but the manufacturing precision deteriorates due to image deformation

Engineering Contradiction:

Improvescanner maneuverabilityVSAvoidthree-dimensional image quality

Core Design Contradiction:

Ease of operationVSManufacturing precision

Solution Approach 1:

The patent captures a reference image before the measurement sequence to establish a stable baseline. This preliminary reference image allows the system to compensate for hand tremors and movements during the actual scanning process, maintaining manufacturing precision while preserving ease of operation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The reference image acts as an intermediary element that mediates between the unstable captured images and the final three-dimensional reconstruction. By using the reference image as a baseline, the system can correct deformations caused by hand tremors and maintain high image quality without requiring the user to maintain perfect stability.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Area of stationary object

If multiple captured images are stitched together, then the coverage area is improved, but the measurement precision deteriorates due to accumulation of deformations

Engineering Contradiction:

Improveoral cavity coverageVSAvoidthree-dimensional image accuracy

Core Design Contradiction:

Area of stationary objectVSMeasurement precision

Solution Approach 1:

The patent captures a reference image before the measurement sequence to establish a stable baseline for the entire oral cavity. This reference image serves as a foundation that prevents the accumulation of deformations when stitching multiple captured images, allowing the system to cover the entire oral cavity while maintaining measurement precision.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses the reference image as a feedback mechanism to continuously correct deformations in the captured images during the stitching process. By comparing the reference image with each captured image and applying correction algorithms, the system maintains measurement precision across the entire oral cavity coverage area.

Inventive Principle:

Principle #23Feedback

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 reduces the likelihood of producing low-quality three-dimensional images by mitigating the effects of rapid movement and hand tremors, resulting in improved image accuracy and stability.

Implementation Method 1

projecting a first light pattern to an object to generate a first image at a first time

Methodology Applied

Scientific EffectLight projection: Light

Data Source

PatentUS20250104321A1Three-dimensional image generation method for generating an image according to two images of different times, and generating a three-dimensional image accordingly

Publication Date: 2025.03.27 QISDA CORP

AI summary

A three-dimensional image generation method includes projecting a first light pattern to an object to generate a first image at a first time, capturing the first image, projecting a second light pattern to the object to generate a second image at a second time, capturing the second image, generating a third image corresponding a third time according to the first image and the second image, and generating a three-dimensional image of the object according to the first image, the second image and the third image. The first time precedes the second time, and the second time precedes the third time.