Disambiguating Machine-Readable Content via Object Type Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for presenting virtual content based on text from objects in a physical environment often face ambiguity, as the same text can refer to multiple subjects, leading to inaccurate virtual content representation.
Innovation Solution
The system uses an image sensor and processors to detect machine-readable content associated with objects, determines the object type, and creates a search query to obtain relevant virtual content, thereby disambiguating the text and providing accurate virtual content based on the object type.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If virtual content is presented based on text from objects in the physical environment, then the system can provide relevant information, but the text may be ambiguous and refer to multiple subjects, leading to inaccurate virtual content representation
Solution Approach 1:
The patent introduces an intermediary disambiguation process that acts as a mediator between the detected text and the virtual content presentation. This intermediary step analyzes the text in context of the physical object and determines the most likely intended subject, thereby resolving ambiguity without requiring direct interpretation of ambiguous text alone
Solution Approach 2:
The system performs preliminary disambiguation analysis before presenting virtual content. By determining the most likely subject reference in advance of content delivery, the system prepares accurate virtual content representations proactively, preventing information loss rather than correcting it after the fact
2Measurement precision
If the system uses object type determination to disambiguate text, then virtual content accuracy improves, but the processing time and computational resources increase
Solution Approach 1:
The system applies partial action by determining only the necessary object type information required for disambiguation, rather than performing exhaustive analysis. It identifies the minimum sufficient object classification needed to resolve the specific ambiguity in context, reducing processing overhead while maintaining precision
Solution Approach 2:
The system dynamically adjusts processing parameters based on the ambiguity level detected. For highly ambiguous text, it performs more thorough object type determination, while for clearly contextualized text, it reduces processing depth, thereby optimizing the balance between precision and processing time
3Reliability
If the system creates search queries using both machine-readable content and object type, then the relevance of obtained virtual content improves, but the complexity of query creation increases
Solution Approach 1:
The system merges the machine-readable content with object type information to create a unified search query. By combining these two data sources into a single coherent query structure, it achieves improved content relevance without requiring separate parallel processing streams, thereby managing complexity through integration rather than multiplication of components
Data Source
AI summary
In one implementation, a method of presenting virtual content is performed by a device including an image sensor, one or more processors, and non-transitory memory. The method includes obtaining, using the image sensor, an image of a physical environment. The method includes detecting, in the image of the physical environment, machine-readable content associated with an object. The method includes determining an object type of the object. The method includes obtaining virtual content based on a search query creating using the machine-readable content and the object type. The method includes displaying the virtual content.