MFP File Name Correction for OCR Space Errors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing file name producing apparatuses often generate unsuitable file names due to mistaken character recognition, especially when character strings are located in photographic regions or shaded backgrounds, leading to unnecessary spaces in the file names.
Innovation Solution
A file name producing apparatus that includes a character string selector and a corrector unit, which can delete or modify candidate character strings to produce a proper file name by removing head spaces or replacing characters, thereby correcting mistaken OCR outputs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If OCR processing is performed to the entire input image including photographic regions, then character extraction coverage is improved, but measurement precision deteriorates due to mistaken recognition in photographic regions
Solution Approach 1:
The patent segments the input image into text regions and non-text regions (such as photographic regions) before performing OCR processing. By dividing the image into distinct processing zones, the system applies character recognition only to text regions, thereby maintaining high recognition accuracy while avoiding mistaken extraction in photographic areas.
Solution Approach 2:
The patent applies different processing qualities to different regions of the image. Text regions undergo full OCR processing with high character extraction quality, while non-text regions are either excluded or processed with reduced quality settings. This local differentiation ensures accurate file name generation from text while preventing spurious character extraction from photographic content.
2Ease of operation
If automatic file name production is implemented, then ease of operation is improved, but reliability deteriorates due to mistaken character recognition
Solution Approach 1:
The patent performs preliminary image analysis to identify and segment text regions before executing OCR processing. By preparing the image structure in advance and pre-identifying valid text areas, the system ensures that subsequent automatic file name generation operates only on confirmed text content, thereby maintaining both automation benefits and high reliability.
Solution Approach 2:
The patent incorporates feedback mechanisms where OCR results are validated against the segmented text regions. If character extraction produces results that do not match the predefined text region boundaries or characteristics, the system adjusts its processing accordingly, ensuring that automatic file name generation maintains high accuracy through continuous validation.
Data Source
AI summary
An MFP (Multifunction Peripheral) is a file name producing apparatus that produces a file name of an image. The MFP selects a candidate character string, which is a file name candidate and in which a head character is a space, from the character strings extracted from the image. The MFP deletes the space that is the head character of the candidate character string, or changes all the characters constituting the candidate character string to other characters. The MFP produces the character string, which is corrected by the deletion or the change, as the file name of the image. Therefore, the proper file name can be produced.