Object Recognition Apparatus Resolving Category Name Conflicts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object recognition systems face challenges in integrating and sharing dictionary data among multiple digital cameras, particularly when images of the same person are categorized differently across devices, leading to conflicts in category names.
Innovation Solution
An object recognition apparatus and method that extracts and compares dictionary information from multiple categories, calculates feature amounts, determines similarity, and integrates category names when similarity exceeds a threshold, allowing for appropriate association and merging of category names.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If dictionary data is integrated among multiple digital cameras, then the sharing function and recognition accuracy are improved, but category name conflicts arise when images of the same person are present in different category names
Solution Approach 1:
The system performs preliminary comparison of category names between dictionary data from different cameras before integration. When a category name conflict is detected (same person with different category names), the system proactively presents the conflict to the user for resolution before completing the integration, preventing inconsistent category names from being merged.
Solution Approach 2:
The system provides feedback to the user by displaying category name conflicts during the dictionary data integration process. The user is informed of discrepancies (e.g., same person categorized differently in different cameras) and can provide corrective input, which is then fed back into the integration process to resolve the conflict and ensure consistent category naming.
2Measurement precision
If manual integration of dictionary data is performed to resolve category name conflicts, then category name accuracy is improved, but the complexity of data management increases
Solution Approach 1:
The system automatically performs feature amount calculation, similarity determination, and conflict detection without requiring manual intervention. The automated process identifies category name conflicts and presents them to the user only when necessary, allowing the system to handle the complex integration process autonomously while minimizing user burden.
Solution Approach 2:
The system acts as an intermediary by automatically comparing category names from different cameras, calculating similarity based on feature amounts, and determining which category names should be integrated. This intermediary process simplifies data management by handling the complex comparison and matching logic automatically, requiring user input only for final confirmation of conflicts.
3Measurement precision
If extensive dictionary data is captured and stored for each camera, then recognition accuracy is improved, but the time and resources required for data management increase
Solution Approach 1:
The system merges dictionary data from multiple digital cameras by integrating category names based on similarity determination. When dictionary data from different cameras is integrated, the system combines the data while automatically resolving category name conflicts, reducing the total amount of duplicate data that needs to be managed across multiple devices while maintaining recognition accuracy.
Solution Approach 2:
The system creates an integrated dictionary data structure that consolidates information from multiple cameras. By copying and integrating category information from different sources while resolving conflicts through automated comparison and user feedback, the system reduces redundant data storage and management time while preserving the comprehensive recognition capabilities.
Data Source
AI summary
An apparatus extracts a first dictionary information associated with a first category from among multiple categories included in a dictionary and second dictionary information associated with a second category from among multiple categories included in the dictionary or another dictionary, calculates a first feature amount and a second feature amount from the first dictionary information and the second dictionary information, respectively, receives an instruction as to whether or not to integrate a name of the first category and a name of the second category in the case where it is determined that a similarity between the calculated first feature amount and second feature amount is greater than a predetermined threshold and that the name of the first category and the name of the second category do not match, and integrates the name of the first category and the name of the second category with the received post-integration name.