Face Image Synthesis Using Consecutive Capture and Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for editing and synthesizing images on portable terminals result in unnatural facial expressions due to direct modification of photos and require inconvenient user interfaces, making it difficult for users to easily select and edit desired face images.
Innovation Solution
A method and apparatus that detect face regions from consecutively photographed images, provide a user-friendly interface for selecting specific face images, and automatically create synthesized images based on pre-stored conditions, using an image pickup unit, face detection unit, facial expression recognition unit, editing unit, and display unit to facilitate easy image editing and synthesis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If direct modification of photographed pictures is used to create facial expressions, then image editing functionality is achieved, but the facial expressions become unnatural and the user interface becomes inconvenient
Solution Approach 1:
The system performs preliminary actions by automatically detecting face regions and capturing multiple images at different time points before the user needs to select. This pre-processing reduces the complexity of the user interface by having the system prepare the data (face regions from multiple images) before presenting selection options to the user, thereby maintaining ease of operation while achieving versatile image editing functionality
2Adaptability or versatility
If multiple images are photographed at predetermined time intervals to extract face images, then more face image options are provided for user selection, but the processing time and complexity increase
Solution Approach 1:
The system segments the complex task of face image processing into distinct modules: image capture at multiple time points, automatic face region detection, and presentation of detected face regions to the user. This segmentation allows the system to handle multiple images systematically, providing diverse face image options while managing processing complexity through structured, modular operations
3Ease of operation
If face regions are detected from consecutively photographed images and displayed for user selection, then users can easily select desired face images, but additional processing steps are required
Solution Approach 1:
The system performs self-service by automatically detecting face regions from consecutively photographed images and preparing them for display without requiring manual user intervention. The automatic face region detection and preparation processes reduce the need for complex user operations, thereby improving ease of selection while the system handles the additional processing steps autonomously
Data Source
AI summary
A support for image processing is provided, comprising: (a) detecting respective face regions from images consecutively photographed for a first person at predetermined time intervals by an image pickup unit to display images of the face regions detected in relation to the first person in a first region of a screen, and providing a user interface for indicating that a specific face image is selected from the face images of the first person displayed in the first region; (b) additionally displaying the specific face image through a second region adjacent to the first region; and (c) displaying a synthesized image using the specific face image as a representative face of the first person, when the specific face image displayed through the second region is selected.