Facial Composite Wireframe System for Natural Image Generation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing facial composite image systems generate unnatural results and lack flexibility for detailed modifications, requiring cumbersome post-processing in software like Photoshop.

Innovation Solution

An integrated apparatus and method for generating facial composite images, featuring a database for face and partial feature information, a wireframe unit for applying active weights, a face composing unit for forming two-dimensional models, and a model transforming unit for user-driven transformations, including facial impression, age, and editing functions, along with a three-dimensional model forming capability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If existing montage systems are used, then facial composite images can be generated, but the results appear unnatural and lack flexibility for detailed modifications

Engineering Contradiction:
Improvenaturalness of facial composite imageVSAvoidflexibility for detailed modifications
Core Design Contradiction:
Manufacturing precisionVSEase of operation

Solution Approach 1:

The system segments the face into multiple controllable regions using a wireframe structure with landmark points. Each landmark can be independently adjusted to modify specific facial features, enabling detailed and natural modifications without affecting the entire face image.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The wireframe structure provides dynamic control over facial features through adjustable landmark points. Users can interactively modify the position and shape of facial features by manipulating the wireframe landmarks, allowing flexible and natural adjustments to the composite image.

Inventive Principle:
Principle #15Dynamics

2Productivity

If existing montage systems are used, then facial composite images can be generated, but post-processing requires cumbersome external software like Photoshop

Engineering Contradiction:
Improvespeed of facial composite image generationVSAvoidneed for external editing software
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system merges the facial composite image generation and editing functions into a single integrated platform. The wireframe-based editing capabilities are incorporated directly into the montage system, eliminating the need for external software like Photoshop and streamlining the entire workflow.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system provides multi-functional capabilities by combining image generation, wireframe-based detailed editing, and feature adjustment in one unified platform. This universal system handles both the creation and refinement of facial composite images without requiring separate tools.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Manufacturing precision

If partial composing method is used, then specific facial features can be selected from database, but the generation process is time-consuming and less accurate

Engineering Contradiction:
Improveaccuracy of facial composite imageVSAvoidtime for image generation
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-establishing a wireframe structure and landmark points on the base face image. This pre-configured framework enables rapid and accurate composition of facial features by simply adjusting the pre-positioned landmarks, significantly reducing generation time while maintaining high accuracy.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS9734613B2Apparatus and method for generating facial composite image, recording medium for performing the method
Publication Date: 2017.08.15 KOREA INST OF SCI & TECH
  • US9734613B2 patent drawing
  • US9734613B2 patent drawing
  • US9734613B2 patent drawing

AI summary

Disclosed is an apparatus for generating a facial composite image, which includes: a database in which face image and partial feature image information is stored; a wireframe unit configured to apply a face wireframe to a basic face sketch image, the face wireframe applying an active weight to each intersecting point; a face composing unit configured to form a two-dimensional face model to which the wireframe is applied, by composing images selected from the database; and a model transforming unit configured to transform the two-dimensional face model according to a user input on the basis of the two-dimensional face model to which the wireframe is applied. Accordingly, a facial composite image with improved accuracy may be generated efficiently.