Scanned Form Division Using Feature Matching and Page Counts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods fail to accurately identify new forms within a stack of scanned documents, requiring users to manually scan new forms first, which is burdensome.
Innovation Solution
An image processing apparatus that analyzes scanned images for feature information, determines similarity to previous images, and divides them based on page counts, automatically identifying and separating new forms from existing ones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If forms are scanned collectively in a stack, then scanning efficiency is improved, but new forms cannot be accurately identified and are computerized as part of preceding forms
Solution Approach 1:
The system performs preliminary analysis of scanned images by comparing feature information against stored templates before final computerization. This preliminary action identifies new forms within the scanned stack, allowing them to be separated and processed correctly rather than being mistakenly computerized as part of preceding forms.
Solution Approach 2:
The system uses feedback mechanisms by comparing feature information of scanned images with stored template information. When a scanned image does not match any existing template, the system identifies it as a new form and triggers appropriate processing, ensuring accurate identification even when forms are scanned collectively.
2Measurement precision
If users manually scan new forms first to enable detection, then new form identification accuracy is improved, but user burden increases
Solution Approach 1:
The system performs self-service by automatically detecting and identifying new forms through feature information comparison without requiring user intervention. The scanning apparatus autonomously analyzes each scanned image, compares it with stored templates, and identifies new forms, eliminating the need for users to manually scan new forms first.
Solution Approach 2:
The system replaces the mechanical approach of manual form scanning with an automated image analysis process. Instead of requiring users to physically scan new forms first, the system uses optical character recognition and feature extraction to automatically identify new forms within any scanned stack, substituting manual operations with automated mechanical and computational processes.
3Measurement precision
If scanned images are divided based on template matching, then document separation accuracy is improved, but new forms with no template are misclassified
Solution Approach 1:
The system dynamically adjusts its document separation strategy by first attempting template-based matching and then evaluating whether the scanned image represents a new form type. This dynamic approach allows the system to adapt to both known and unknown form types, improving versatility while maintaining separation accuracy for standard forms.
Solution Approach 2:
The system changes the matching parameters by comparing feature information against stored templates and using the page count associated with matched templates to determine division points. When no template matches are found, the system identifies the image as a new form type and adjusts the separation logic accordingly, enabling accurate handling of both existing and new form types.
Data Source
AI summary
An image processing apparatus obtains scanned images by scanning forms of a plurality of types; manages page counts associated with feature information of previous scanned images of respective form types; analyzes each of the scanned images to determine, based on the feature information, whether the analyzed scanned image is similar to any of the previous scanned images; and divides the scanned images based on a scanned image to determined to be similar to any of the previous scanned images and the page count associated with the any of the previous scanned images.