Virtual Makeup Database Expansion via Automated Feature Capture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing virtual makeup systems lack the ability to automatically update and expand their makeup pattern databases based on user-input images, limiting their practicality and user convenience.
Innovation Solution
A method and platform for establishing virtual makeup data that includes receiving an image, identifying and adjusting the makeup face, defining areas for makeup categories, capturing and comparing makeup features, and adding new patterns to the database when differences are detected, using modules such as an input module, image processing module, makeup feature capturing module, and makeup feature classifying module.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If virtual makeup systems use a fixed database of makeup patterns, then the system structure is simple and easy to implement, but the adaptability and user convenience are limited
Solution Approach 1:
The system automatically captures makeup features from user images, compares them with existing patterns, and adds new patterns to the database without requiring manual intervention. This self-service mechanism enables the system to autonomously expand its makeup pattern library, improving adaptability while maintaining operational simplicity
Solution Approach 2:
The system pre-establishes a database structure with categorized makeup patterns and feature extraction frameworks before actual use. This preliminary preparation allows the system to quickly process and integrate new makeup patterns when users provide images, reducing the complexity of real-time processing while enhancing adaptability
2Productivity
If the makeup pattern database is manually updated, then the system complexity is low, but the productivity and efficiency of database expansion are reduced
Solution Approach 1:
The system replaces manual mechanical processes of database updating with automated image processing and pattern recognition algorithms. The automated system captures makeup features from images, extracts relevant data, and integrates new patterns into the database without human intervention, dramatically increasing productivity while implementing full automation
Solution Approach 2:
The system continuously compares newly captured makeup features with existing database patterns and uses this feedback to determine whether to add new patterns. This feedback mechanism ensures that the automated database expansion process is efficient and productive, adding only genuinely new patterns while maintaining system organization
3Adaptability or versatility
If the system processes and analyzes user images to extract makeup features, then the adaptability and customization are improved, but the processing time and computational resources increase
Solution Approach 1:
The system divides the face image into multiple regions corresponding to different makeup categories (eyes, lips, cheeks, etc.) and processes each region separately to extract specific makeup features. This segmentation approach enables targeted feature extraction that improves customization capabilities while reducing overall processing time by focusing computational resources on relevant areas only
Solution Approach 2:
The system applies different processing strategies to different facial regions based on their specific characteristics. High-detail processing is applied to areas requiring precise makeup pattern recognition, while simplified processing is used for other areas, optimizing the balance between customization quality and processing efficiency
4Measurement precision
If the system compares captured features with existing database patterns, then the accuracy of pattern recognition is improved, but the computational complexity and processing time increase
Solution Approach 1:
The system performs partial comparison by focusing on key discriminative features of makeup patterns rather than analyzing all possible features. This selective approach maintains high recognition accuracy by comparing only the most relevant features while significantly reducing computational complexity and processing requirements
Data Source
AI summary
A method of establishing virtual makeup data, an electronic device and a non-transitory computer readable storage medium are provided. The method includes: adjusting a scope of the makeup face in the first image to match a predetermined face scope in a predetermined image; defining a plurality of areas on the adjusted makeup face, and each of the areas corresponds to a makeup category; capturing a plurality of first makeup features of at least one of the target makeup category in the makeup category; comparing the first makeup features with a plurality of second makeup features in the database whose target makeup category are same; adding a first makeup pattern including the first makeup features to the target makeup category of the database when the first makeup feature is different from the second makeup feature.