Personalized Makeup Transfer in Face Image Generation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing face image generation systems fail to reflect individual user preferences and conditions in makeup applications, resulting in uniform and uncustomized post-makeup images.

Innovation Solution

A face image generation device that extracts user makeup features from a first face image and applies them to generate a second face image with customized makeup based on standard data for a different pattern, incorporating user preferences and conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If uniform reference makeup is applied to generate post-makeup images for different situations, then the generation process is simple and efficient, but user preferences and individual makeup features are not reflected

Engineering Contradiction:
Improvemakeup image generation efficiencyVSAvoidcustomization to user preferences
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent segments the makeup generation process into two independent components: (1) situation-specific standard makeup patterns that define the base makeup style for different occasions, and (2) user-specific makeup features that capture individual preferences. This segmentation allows the system to maintain efficiency through pre-defined patterns while incorporating customization through user feature extraction and integration.

Inventive Principle:
Principle #1Segmentation

2Stability of the object's composition

If standardized makeup patterns are used for different situations, then consistency across situations is maintained, but individual user characteristics are lost

Engineering Contradiction:
Improvemakeup consistency across situationsVSAvoiduser makeup feature information
Core Design Contradiction:
Stability of the object's compositionVSLoss of information

Solution Approach 1:

The patent merges two previously separate elements into a unified makeup generation system: the situation-specific standard makeup pattern and the user-specific makeup features. The merging process combines these elements through image synthesis, producing a final post-makeup image that simultaneously maintains situation-appropriate consistency and incorporates individual user characteristics without information loss.

Inventive Principle:
Principle #5Merging (Combining)

3Adaptability or versatility

If user-specific makeup features are extracted and integrated into different situation patterns, then customization is achieved, but the complexity of the generation process increases

Engineering Contradiction:
Improvepersonalization capabilityVSAvoidmakeup generation system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-extracting and storing user-specific makeup features in advance, creating a reusable user profile. This preliminary extraction of features (such as skin tone, facial structure, and preferred makeup style) allows the system to quickly apply customization across different situations without performing complex extraction operations each time, thereby reducing real-time processing complexity while maintaining high personalization capability.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS12524928B2Face image generation device
Publication Date: 2026.01.13 NTT DOCOMO INC
  • US12524928B2 patent drawing
  • US12524928B2 patent drawing
  • US12524928B2 patent drawing

AI summary

A face image generation device includes: a first face image acquiring unit configured to acquire a first face image to which makeup corresponding to a first pattern has been applied by a user; a feature extracting unit configured to extract features of the makeup of the user on the basis of the first face image and first standard data relating to features of standard makeup corresponding to the first pattern; a second face image generating unit configured to generate a second face image to which makeup corresponding to a second pattern has been applied by reflecting the features of the makeup of the user extracted by the feature extracting unit in second standard data relating to features of standard makeup corresponding to the second pattern; and a presentation unit configured to present the second face image generated by the second face image generating unit to the user.