Search Apparatus Error Detection for OCR Character Strings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Search systems using OCR-recognized character strings for search keys often result in erroneous results, leading to time-consuming manual verification and re-search processes, especially when handwritten characters are involved.
Innovation Solution
A search apparatus with a character string acquisition unit, a search unit, a determining unit, and a job switching unit that assesses errors and automatically requests manual input or verification based on error determination, reducing unnecessary verification and re-search operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual verification of all search results is performed, then search accuracy is improved, but time consumption increases
Solution Approach 1:
The system performs self-verification by automatically determining whether error factors are present in OCR-recognized character strings. The determining unit assesses the reliability of recognized characters and makes automated decisions about whether manual verification is needed, allowing the system to serve itself rather than requiring constant human intervention for verification.
Solution Approach 2:
The system implements feedback mechanisms where search results and OCR recognition accuracy are continuously evaluated. The determining unit uses feedback from previous recognition accuracy and error factor analysis to dynamically adjust verification requirements, reducing unnecessary verification while maintaining search accuracy through intelligent decision-making.
2Productivity
If OCR recognition is used for search keys, then input efficiency is improved, but error rate increases
Solution Approach 1:
The system performs preliminary error detection and assessment before executing searches. The determining unit evaluates whether error factors are present in the OCR-recognized character strings beforehand, allowing the system to correct or flag potential errors before they affect search accuracy, thus maintaining both efficiency and reliability.
Solution Approach 2:
The determining unit acts as an intermediary between OCR recognition and search execution. It assesses the quality of recognized character strings and determines whether manual input or verification is needed, serving as a mediator that filters out erroneous recognitions while preserving efficient automated processing for high-quality inputs.
3Loss of time
If automated error determination is implemented, then verification time is reduced, but system complexity increases
Solution Approach 1:
The system segments the verification process into distinct functional units: character string acquisition, error factor determination, and job switching. This modular segmentation allows each component to perform its specific function efficiently, reducing overall system complexity while enabling automated error determination and time-saving verification processes.
Data Source
AI summary
A search apparatus includes a character string acquisition unit that acquires a character string recognized by a character recognition device, a search unit that sends to an information source the character sting as a search key and retrieves search result information responsive to the search key out of information stored on the information source, a determining unit that determines whether an error factor including at least one of a cause for an erroneous search and an erroneous search result is present, and a job switching unit that requests a manual input job to be performed to input a search key that is to replace the character string if the determining unit has determined that the error factor is present, and requests a verification job to be performed on the search result information if the determining unit has determined that the error factor is not present.