Electronic Document Generation with OCR Character Size Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic document generation systems face issues with accurately positioning character strings from OCR processing results when these results are generated on a cloud server and embedded into electronic documents, due to the lack of character size information returned by the server, leading to shifts and misalignment, especially when the client device cannot arbitrarily set the output form.
Innovation Solution
An electronic document generation system that includes an extraction unit to identify processing target areas from scanned images, a detection unit to determine character sizes, and a generation unit to accurately arrange character strings based on these sizes, ensuring proper alignment by determining the arrangement-direction character size and orthogonal-direction character size for precise positioning of OCR results within the document.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If OCR processing is performed on a cloud server and only the processing result is returned to the client device, then the processing load on the client device is reduced, but the character size information is lost causing misalignment between OCR text and character images
Solution Approach 1:
The patent extracts only the necessary character size information from the OCR processing result and returns it to the client device along with the processed text. This selective extraction maintains the benefit of cloud-based processing while preserving the critical alignment information that would otherwise be lost.
Solution Approach 2:
The cloud server performs preliminary OCR processing and extracts character size information in advance, preparing the data in a format that enables accurate positioning. This preliminary action ensures that when the result is returned to the client, all necessary information for correct alignment is already available.
2Device complexity
If character strings from OCR results are arranged in the electronic document without character size information, then the document generation process is simplified, but the positioning accuracy of character strings deteriorates
Solution Approach 1:
The patent introduces character size as a critical parameter in the document generation process. By obtaining and utilizing character size information from the OCR processing result, the system can accurately position character strings in the electronic document while maintaining a relatively simple generation process.
3Ease of manufacture
If the cloud server outputs processing results in a fixed form, then the server implementation is simplified, but the client device cannot arbitrarily set the output form leading to alignment issues
Solution Approach 1:
The patent makes the cloud server's OCR processing result universally applicable by including both the processed text and character size information in a standardized format. This universal output format can be used by any client device to achieve accurate alignment, combining server-side simplicity with client-side flexibility.
Data Source
AI summary
An electronic document generation apparatus extracts a processing target area including a row area from a scanned image of an original document and detects the dimensions of the row area, the row area being an area of either a whole or partial range of a row of character string arranged in one direction in the scanned image. The apparatus determines an arrangement-direction character size on the basis of the dimensions of the row area, and sends out image data of the processing target area and an instruction to perform OCR processing on the processing target area to an external apparatus. The apparatus then receives a processing result of the OCR processing from the external apparatus, and arranges a character string of the processing result in the electronic document on the basis of the arrangement-direction character size to generate an electronic document.