Joint Feature Comparison Space for Material Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for selecting materials in graphical design environments often disregard visual characteristics of materials, leading to inefficient searches and the allocation of computing resources to unsuitable materials.
Innovation Solution
A material search computing system generates a joint feature comparison space using joint image-text features extracted from rendered digital images of surface material data objects, allowing for more accurate searches by comparing visual and textual features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If text input search techniques are used to identify materials, then the search process is simple to implement, but the search accuracy deteriorates because visual characteristics of materials are disregarded
Solution Approach 1:
The patent merges text-based search with image-based visual feature comparison by creating a joint feature comparison space that combines both text embeddings and image embeddings. This allows the system to maintain the simplicity of text input while incorporating visual characteristics for accurate material identification, resolving the contradiction between ease of implementation and search accuracy.
2Reliability
If all material data objects are included in search results, then comprehensive results are provided, but computational resources are wasted on less relevant materials
Solution Approach 1:
The patent applies partial action by performing detailed visual feature comparison only on materials that pass the initial text-based relevance filter. Instead of comparing all materials equally, the system performs exhaustive visual comparison only on the subset of materials that are textually relevant, thereby maintaining comprehensiveness for relevant materials while avoiding wasteful computational resources on irrelevant ones.
3Measurement precision
If visual characteristics are incorporated into material search, then search accuracy is improved, but system complexity increases
Solution Approach 1:
The patent introduces a joint feature comparison space as an intermediary that bridges text-based search and image-based visual comparison. This intermediary space embeds both text and image features in a unified vector space, allowing the system to incorporate visual characteristics for improved accuracy while managing complexity through a structured intermediate representation rather than direct complex image processing.
Data Source
AI summary
A material search computing system generates a joint feature comparison space by combining joint image-text features of surface material data objects. The joint feature comparison space is a consistent comparison space. The material search computing system extracts a query joint feature set from a query data object that includes text data or image data. In addition, the material search computing system compares the query joint feature set to the joint image-text features included in the joint feature comparison space. Based on the comparison, the material search computing system identifies a result joint feature set and associated result surface material data objects. The material search computing system generates material query result data describing the result surface material data objects, and provides the material query result data to an additional computing system.