Scanned Page Ordering Using OCR Certainty and Rule Setting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image forming apparatuses face challenges in efficiently ordering and dividing scanned page data, particularly in identifying and extracting page numbers and layouts, which can be cumbersome for users and often require manual rule creation.
Innovation Solution
An information processing apparatus and method that utilizes optical character recognition (OCR) to analyze page layouts, classifies pages based on ordering rules, calculates page number certainty, and allows users to set rules through a graphical user interface, with machine learning assisting in uncertain cases.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual rule creation is used for ordering and dividing scanned page data, then users can have full control over the ordering process, but user effort and time consumption increase significantly
Solution Approach 1:
The system performs self-service by automatically analyzing scanned page data, extracting page numbers through OCR, and ordering pages without requiring manual user intervention. The apparatus autonomously completes the ordering task by processing the scanned images and generating the ordered output, thereby eliminating the need for users to manually create ordering rules.
Solution Approach 2:
The patent replaces the mechanical manual process of rule creation with an automated optical character recognition (OCR) system. Instead of users manually examining and ordering pages, the system uses OCR technology to automatically detect and extract page numbers from scanned images, substituting human mechanical effort with automated optical and computational processes.
2Productivity
If automated OCR and classification are used for page ordering, then processing speed and efficiency improve, but accuracy in extracting page numbers and layouts may deteriorate
Solution Approach 1:
The system implements feedback by calculating certainty values for extracted page numbers and using this information to guide further processing. When the certainty of extracted page numbers is low, the system can adjust its processing approach or seek additional information, thereby improving accuracy while maintaining efficient automated processing for high-certainty cases.
Solution Approach 2:
The patent changes the parameter of certainty calculation to optimize the balance between processing efficiency and accuracy. By introducing and calculating certainty values for page number extraction, the system can dynamically adjust its behavior based on the confidence level, improving accuracy when needed while maintaining speed when certainty is high.
3Reliability
If complex OCR and classification processes are implemented, then ordering accuracy improves, but device complexity and computational requirements increase
Solution Approach 1:
The system segments the complex ordering process into distinct functional modules: OCR processing for text extraction, classification for categorizing pages based on extracted information, and certainty calculation for quality assessment. This segmentation allows each component to be optimized independently while working together to achieve high ordering accuracy without requiring the entire system to be overly complex.
Solution Approach 2:
The patent implements multi-functional components that perform multiple tasks. The OCR unit not only extracts text but also identifies page numbers and layouts. The classification unit uses the extracted information to categorize and order pages. This universality reduces overall system complexity by having components serve multiple purposes rather than requiring separate dedicated systems for each function.
Data Source
AI summary
Provided is an information processing apparatus that easily sets rules for ordering a plurality of scanned page data. The OCR unit performs optical character recognition for character and layout in a page for each of the plurality of page data. The rule order unit classifies the characters and layouts that are performed optical character recognition by the OCR unit based on the page ordering rules, extracts the page numbers, and calculates the certainty of the page numbers. The rule setting unit presents the certainty calculated by the rule order unit to the user and causes the user to set the rule.