Shape-Based Search Using Refinement Shape Hierarchy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional search methods for electronic records, such as digitized photographs, require manual keyword descriptions that are labor-intensive and prone to errors, and vary between individuals, making it difficult to refine search results based on item shapes.
Innovation Solution
A shape-based search system that groups inventory items into categories and creates refinement shapes, using histogram descriptors to associate images with representative shapes, allowing for the creation of a refinement-shape hierarchy and enabling searches based on shape similarities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual keyword descriptions are used to refine search results, then search precision can be improved, but labor intensity and error rates increase
Solution Approach 1:
The system automatically generates shape-based search queries by analyzing image data and extracting shape descriptors, eliminating the need for manual keyword input. The search system self-services by automatically refining results based on shape characteristics, thereby maintaining high search precision while reducing labor intensity to zero.
Solution Approach 2:
The patent replaces manual mechanical keyword input with an automated computational system that extracts shape descriptors from images. The mechanical action of manually typing and selecting keywords is substituted by automated image processing algorithms that compute shape-based query parameters, achieving both high precision and productivity.
2Measurement precision
If manual keyword descriptions are used, then search results can be refined, but variability and errors in descriptions increase
Solution Approach 1:
The system changes the search parameter from subjective textual keywords to objective shape descriptors derived from image data. By transforming the search basis from human-generated text to computationally extracted geometric parameters, the system eliminates variability and errors in descriptions while maintaining consistent and reliable search refinement.
Solution Approach 2:
The patent substitutes manual keyword generation with automated shape descriptor extraction algorithms. This replacement eliminates the human element that introduces variability and errors, ensuring consistent and reliable search results across different users and contexts.
3Productivity
If shape-based search is implemented, then search efficiency improves, but system complexity increases
Solution Approach 1:
The system segments the search process into distinct modules: image data collection, shape descriptor extraction, query generation, and search execution. By dividing the complex shape-based search system into manageable functional segments, the patent achieves high search efficiency while making the overall system complexity more manageable and maintainable.
Data Source
AI summary
Shape-based search of a collection of content associated with one or more images of inventory items (“inventory images”) is enabled at least in part by associating the collection of content and/or its associated inventory images with representative refinement shapes. Inventory items may be grouped into categories and at least one refinement shape may be created for each of the categories. A refinement-shape hierarchy may be created by arranging the refinement shapes into parent and child refinement shapes. Inventory images may be associated to at least one of the refinement shapes of the refinement-shape hierarchy based at least in part on similarities between the refinement shapes and shapes of the inventory items reflected in the inventory images.