Smile Line Image Alignment Using Feature Points and Templates

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for designing a smile line in smile design are inefficient and time-consuming, lacking precision and user convenience in predicting the outcome of corrective treatments such as veneers or laminates.

Innovation Solution

An image processing method and device that receives and fits image data to apply a template for smile line design, aligns image data based on feature points and lines, and arranges data according to an openness parameter, allowing for accurate and quick prediction of the smile line after correction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual methods are used for smile line design and image alignment, then flexibility and customization are possible, but the process becomes time-consuming and inefficient

Engineering Contradiction:
Improveefficiency of smile line designVSAvoidtime required for treatment planning
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The system performs automatic image fitting, feature point detection, and template application without requiring manual intervention. The processor autonomously aligns patient images with templates by detecting feature points and calculating transformation parameters, eliminating the need for time-consuming manual adjustment while maintaining design flexibility

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

Multiple smile line templates are pre-prepared with various degrees of openness before the actual treatment planning process. These templates are stored in advance and automatically selected and applied based on the patient's specific conditions, reducing the time required for real-time design iterations

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If multiple image data with different openness degrees are processed manually, then comprehensive analysis is possible, but user effort and complexity increase

Engineering Contradiction:
Improveaccuracy of smile line predictionVSAvoiduser effort in processing image data
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system automatically detects feature points on multiple image datasets with different openness degrees and performs alignment without user intervention. The processor independently calculates transformation parameters and superimposes templates on each image, eliminating the need for manual processing while ensuring consistent and accurate results across all datasets

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The processing of multiple image datasets is divided into independent steps: feature point detection, image fitting, template selection, and superimposition. Each step is handled automatically by the processor, allowing comprehensive analysis of multiple openness degrees without increasing user effort or operational complexity

Inventive Principle:
Principle #1Segmentation

3Manufacturing precision

If feature points and lines are used for image fitting, then alignment accuracy is improved, but processing complexity increases

Engineering Contradiction:
Improveaccuracy of image alignmentVSAvoidcomplexity of fitting algorithm
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The processor automatically detects feature points and generates feature lines without requiring manual input or complex user-defined parameters. The system independently calculates the optimal fitting transformation based on detected feature points, simplifying the interface while maintaining high alignment accuracy through automated geometric processing

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4238528B1Image processing method and apparatus using same
Publication Date: 2026.03.11 MEDIT CORP
  • EP4238528B1 patent drawingFigure 1
  • EP4238528B1 patent drawingFigure 2
  • EP4238528B1 patent drawingFigure 3

AI summary

An image processing method according to the present invention comprises the steps of : receiving at least one image data; assigning a plurality of feature points to the image data; fitting the image data to have at least one of a predetermined size and a predetermined angle on the basis of at least one feature line generated by connecting at least two of the feature points; and designing a smile line by applying at least one template to a feature region generated by the feature points of the fitted image data.