Intraoral Scanner 3D Point Cloud Filtering via Color Pattern Recognition

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Intraoral scanning systems face challenges in accurately capturing 3D data due to the presence of unwanted objects like utensils and movable tissues, as well as stains or particles on tooth surfaces, which interfere with the scanning process and require time-consuming editing and rescanning.

Innovation Solution

A method that filters out 3D point cloud data corresponding to labelled image elements representing utensils or tooth areas with stains or particles, using color pattern recognition to identify and remove these unwanted data points, thereby improving the accuracy and efficiency of the scanning process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional manual editing methods are used to remove unwanted scan data, then measurement precision can be maintained, but loss of time increases significantly

Engineering Contradiction:

Improveaccuracy of 3D dataVSAvoidtime for editing and rescanning

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs automatic identification and filtering of unwanted scan data through algorithmic analysis of color patterns and geometric features, eliminating the need for manual operator intervention in data cleaning processes

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Manual editing operations are replaced by automated computational algorithms that analyze scan data characteristics, identify unwanted elements based on color and geometry, and filter them programmatically

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If utensils and retractors are used during scanning to manage movable tissues, then ease of operation improves, but object-generated harmful factors increase due to unwanted data incorporation

Engineering Contradiction:

Improveease of managing movable tissuesVSAvoidunwanted data from utensils

Core Design Contradiction:

Ease of operationVSObject-generated harmful factors

Solution Approach 1:

The system extracts and removes data corresponding to utensils and retractors from the scan dataset by identifying their characteristic color patterns and geometric features, separating desired dental tissue data from unwanted instrument data

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The presence of utensils and retractors, which originally caused harmful interference, is converted into a beneficial situation by using their distinctive color patterns as identification markers for automatic filtering and removal

Inventive Principle:

Principle #22Blessing in disguise (Convert harm into benefit)

3Measurement precision

If multiple rescanning operations are performed to correct unwanted data, then measurement precision is maintained, but productivity decreases

Engineering Contradiction:

Improveaccuracy of final 3D modelVSAvoidscanning efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system performs preliminary filtering of unwanted data during the initial scanning operation by automatically identifying and removing unwanted elements based on color and geometric analysis, preventing the need for subsequent rescanning operations

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11446125B2Method for intraoral scanning directed to a method of processing and filtering scan data gathered from an intraoral scanner

Publication Date: 2022.09.20 NOBEL BIOCARE SERVICES AG

AI summary

A method and apparatus for generating and displaying a 3D representation of a portion an intraoral scene is provided. The method includes determining 3D point cloud data representing a part of an intraoral scene in a point cloud coordinate space. A colour image of the same part of the intraoral scene is acquired in camera coordinate space. The colour image elements are labelled that are within a region of the image representing a surface of said intraoral scene, which should preferably not be included in said 3D representation. A labelled and applicably transformed colour image is then mapped onto the 3D point cloud data, whereby the 3D point cloud data points that map onto labelled colour image elements are removed or filtered out. A 3D representation is generated from said filtered 3D point cloud data, which does not include any of the surfaces represented by the labelled colour image elements.