Digital Artwork Suggestion System Using Co-occurrence Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems for graphic designers struggle to suggest relevant secondary objects and backgrounds for digital artwork, often providing either obvious or irrelevant suggestions, and are unable to generate ideas based on entire sets of images, leading to creative blocks during the design process.
Innovation Solution
A computing device implements a suggestion system that uses a co-occurrence graph to identify relevant objects by analyzing the co-occurrence relationships between objects in digital artwork, allowing for real-time suggestions that enrich the artwork with objects that are likely to be relevant and creative, and can animate or augment static reality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional systems use human user inputs to identify secondary objects, then the system can generate suggestions for digital artwork, but the suggestions are often either already apparent to the designer or have no relevancy to the message being communicated
Solution Approach 1:
The system pre-processes a large corpus of images to build co-occurrence graphs and object relationship databases before actual design work begins. This preliminary analysis of how objects appear together in professional designs enables the system to provide contextually relevant suggestions without requiring manual input during the design process.
Solution Approach 2:
The system analyzes the primary object and existing elements in the digital artwork, then provides suggestions based on co-occurrence patterns. The suggestions are generated with feedback loops that consider the specific context of the artwork, ensuring relevancy to the message being communicated rather than providing generic suggestions.
2Quantity of substance
If conventional systems rely on searching for images of other designs, then the system can identify secondary objects that frequently appear, but the suggestions are limited and often generic
Solution Approach 1:
The system transitions from two-dimensional image searching to multi-dimensional analysis by building co-occurrence graphs that capture relationships between objects across entire sets of images. This enables the system to suggest objects based on complex relational patterns rather than simple frequency counts, providing more creative and contextually appropriate suggestions.
Solution Approach 2:
The system changes the parameter of analysis from simple object frequency to co-occurrence relationships and contextual relevance. By analyzing how objects appear together in professional designs and using this data to weight suggestions, the system provides more versatile and creative options rather than generic frequent items.
3Loss of information
If the system analyzes entire sets of images to generate suggestions, then the suggestions can be based on comprehensive co-occurrence data, but the processing time and computational resources increase
Solution Approach 1:
The system performs comprehensive analysis of entire image sets beforehand to build co-occurrence graphs and object relationship databases. This pre-processing stores the computational results in structured formats that enable rapid querying during actual design work, eliminating the need for time-consuming analysis during the creative process.
Solution Approach 2:
The system pre-computes co-occurrence statistics and object relationships from large image corpora, storing these results in graphs and databases that can be quickly queried. This preliminary processing transforms raw image data into structured knowledge that enables fast suggestion generation without requiring real-time analysis of entire image sets.
Data Source
AI summary
In implementations of suggestions to enrich digital artwork, a suggestion system identifies a first object in the digital artwork and suggests a second object for addition to the digital artwork based on the second object having a co-occurrence relationship with the first object. The co-occurrence relationship is based on the first object and the second object appearing together in an image of an image set. A user may select the second object to add to the artwork or the user may be inspired by the second object to enrich the digital artwork.