Preference-Based Image Generation Using Object-Aware Layout
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices lack the ability to generate personalized images that reflect a user's unique preferences and characteristics, making it difficult to create relevant background images and album covers with minimal user input.
Innovation Solution
An electronic device equipped with a processor and memory that recognizes objects in images, determines categories, selects target objects, and arranges them based on determined categories to generate new images for display, allowing for personalized background images and album covers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If automatic image generation based on object recognition is implemented, then user convenience and personalization are improved, but device complexity increases
Solution Approach 1:
The system segments the image generation process into distinct functional modules: object recognition module, category determination module, arrangement information generation module, and image synthesis module. Each module handles a specific task independently, making the complex system manageable and maintainable while achieving automatic personalized image generation
Solution Approach 2:
The patent introduces an intermediary processing layer that includes a processor and memory that mediate between the raw image data and the final generated image. This intermediary layer performs object recognition, category determination, and arrangement calculation, bridging the gap between simple input images and complex output images
2Productivity
If automated object recognition and arrangement is performed, then productivity is improved, but measurement precision requirements increase
Solution Approach 1:
The system performs partial object recognition by focusing on identifying key objects and their categories rather than analyzing every pixel in detail. This partial action approach maintains sufficient precision for the application while significantly improving processing speed and productivity
Solution Approach 2:
The patent replaces manual image analysis with automated computer vision algorithms that use machine learning models for object recognition and category determination. This substitution enables high-speed processing while maintaining accuracy through trained neural networks rather than manual measurement
3Adaptability or versatility
If multiple displays of different sizes are supported, then adaptability is improved, but device complexity increases
Solution Approach 1:
The image generation system is designed with universal functionality to serve multiple display types. The arrangement information generation module creates layouts that can be adapted to various screen sizes and aspect ratios, allowing the same system to function on different display devices without requiring separate optimization for each
Solution Approach 2:
The system dynamically adjusts the generated image composition based on the target display characteristics. The arrangement information is generated flexibly to accommodate different display sizes, allowing the same object recognition results to be adapted for various display configurations through dynamic layout adjustment
Data Source
AI summary
Various embodiments of the disclosure may include a display (160), a processor (120), and a memory (130). The memory stores instructions that, when executed by the processor, cause an electronic device to recognize one or more objects included in one or more stored images, determine categories corresponding to the recognized one or more objects, select at least one target object to be displayed on the display among the recognized one or more objects, determine arrangement information of the at least one target object based on the determined categories and the images, and provide a new image for display on the display in which the at least one target object is arranged based on the arrangement information. Various other embodiments are also possible.