Image Layout Generation Using Object Correlation Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional image layout methods are limited in generating variations and cannot consider the relationship between the target person and other persons, resulting in a restricted range of layout images.
Innovation Solution
An apparatus and method that acquire main object information and object correlation information to extract images including the main object and related objects, using a layout template to generate a layout image that incorporates both the main object and related objects, allowing for a more diverse range of layout images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional image layout methods focus only on the target person, then the layout generation process is simple, but the variety of layout images that can be generated is limited
Solution Approach 1:
The patent segments the object selection process into multiple independent categories (target person, pets, plants, landscapes, buildings, vehicles, food, beverages, and other objects). Each category can be independently selected and combined, enabling diverse layout variations without significantly complicating the overall generation process.
Solution Approach 2:
The patent introduces dynamic selection capabilities where users can flexibly choose which object categories to include in each layout. The system adapts to different combination preferences and can generate varied layouts by dynamically selecting from multiple object types rather than following a fixed single-object pattern.
2Loss of information
If conventional image layout methods only consider the target person, then the processing is straightforward, but the relationship between the target person and other persons cannot be considered
Solution Approach 1:
The patent merges multiple object categories (target person, pets, plants, landscapes, buildings, vehicles, food, beverages, and other objects) into a unified layout generation framework. This combination preserves relationship information by allowing multiple object types to coexist in the same layout while maintaining relatively simple processing through standardized extraction and placement procedures.
Data Source
AI summary
An apparatus includes a first acquisition unit configured to acquire main object information specifying a main object in generation of a layout image, a second acquisition unit configured to acquire object correlation information specifying an object having a correlation with the main object, an extraction unit configured to extract at least one image including the main object and at least one image including the object having the correlation with the main object from a plurality of images based on the acquired main object information and the acquired object correlation information acquired, and a generation unit configured to generate, using a layout template, a layout image in which the at least one image extracted by the extraction unit and including the main object and the at least one image extracted by the extraction unit and including the object having the correlation with the main object are laid out therein.