Normalized Confidence Levels for Multi-Source Image Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing recognition engine systems cannot compare confidence levels from different image sources, making it impossible to identify the 'best read' of recognition results across multiple image sources.
Innovation Solution
A method is implemented to process recognition results from multiple image sources, converting confidence levels into normalized levels that can be compared across sources, allowing the selection of the image source providing the best recognition results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If confidence levels from multiple image sources are used, then recognition accuracy can be improved, but confidence levels from different sources cannot be compared
Solution Approach 1:
The patent transforms confidence levels from different image sources by applying source-specific adjustment values. Each image source has an associated confidence level adjustment value that modifies its raw confidence level, enabling standardized comparison across sources while preserving the ability to handle multiple source types and their characteristics
2Measurement precision
If multiple image sources are processed, then the best recognition result can be identified, but normalized confidence levels must be stored and managed
Solution Approach 1:
The patent pre-calculates and stores confidence level adjustment values for each image source in advance. These adjustment values are determined based on source characteristics and performance, allowing rapid normalization during operation without real-time complex computations, thus reducing processing time and resource requirements
Data Source
AI summary
A method comprises receiving from a first data source first recognition results which are associated with the first data source, and receiving from a second data source second recognition results which are associated with the second data source. The method further comprises, processing a first set of confidence levels associated with the first recognition results to provide a first set of normalized confidence levels associated with the first data source, and processing a second set of confidence levels associated with the second recognition results to provide a second set of normalized confidence levels associated with the second data source. The method also comprises storing the first set of normalized confidence levels associated with the first data source in a first table of normalized confidence levels and the second set of normalized confidence levels associated with the second data source in a second table of normalized confidence levels.