Automated Region Identification for Fax Data Input
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems require manual specification of identification information for FAX data input, leading to a time-consuming process due to the need for users to manually identify regions for character recognition and input information.
Innovation Solution
A system that generates regions for character recognition, compares their coordinates with historical data, determines identification information, and executes a script to automatically input recognized text into an application, thereby streamlining the input process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual specification of identification information is used for FAX data input, then the system can accurately identify regions for character recognition, but the input process becomes time-consuming and inefficient
Solution Approach 1:
The system performs preliminary actions by automatically generating region coordinates based on historical transmission data before the actual character recognition process. The coordinate generation unit creates region coordinates by referencing stored historical coordinates, eliminating the need for manual specification and reducing input time while maintaining identification accuracy.
2Productivity
If automated region generation is implemented, then the input speed increases significantly, but the complexity of the system increases due to additional processing units
Solution Approach 1:
The system achieves multi-functionality by integrating the coordinate generation unit that serves multiple purposes: it generates region coordinates for character recognition, references historical transmission data, and adapts to different FAX document formats. This universal approach increases input speed without proportionally increasing system complexity.
3Measurement precision
If historical transmission data is stored and referenced, then the accuracy of region identification improves, but the storage requirements and data processing load increase
Solution Approach 1:
The system extracts only the essential coordinate information from historical transmission data that is needed for region identification, rather than storing and processing complete historical records. This extraction approach improves region identification accuracy while minimizing the storage volume and data processing load.
Data Source
AI summary
A system includes a storage unit, a generation unit, a comparison unit, a determination unit, and an execution unit. The storage unit stores coordinates of regions included in a document and identification information of the regions. The generation unit generates regions to be subjected to character recognition in a newly-received document. The comparison unit compares the generated regions coordinates and the stored regions coordinates. The determination unit determines identification information corresponding to the generated regions coordinates according to the identification information corresponding to the regions stored in the storage unit and a comparison result of the comparison unit. The execution unit specifies a script for inputting, to an application, text information obtained by the character recognition performed on the generated regions in accordance with the determined identification information and executes the specified script. The storage unit stores the generated regions coordinates and the determined identification information of the regions.