Context-Aware Digital Image Data Field Manipulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current digital image capture technologies lack the flexibility to allow users to manipulate or post-edit recognized content in images, such as receipts or menus, in a context-specific manner, preventing users from performing operations like recalculating sales tax or obscuring sensitive information.
Innovation Solution
A digital image processing system that assigns context to images based on user input or automatic pattern recognition, allowing users to manipulate specific data fields, perform context-specific calculations, and generate output images in various formats, including obscuring unwanted fields.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If current OCR software is used to identify text in images, then text recognition is achieved, but the ability to manipulate or post-edit recognized content in a context-specific manner is lost
Solution Approach 1:
The patent segments the recognized content into structured data fields (e.g., item name, price, quantity, total) based on the identified context type. This segmentation allows users to selectively manipulate specific fields (such as modifying prices or quantities) while maintaining the overall document structure, thereby enabling flexible context-specific operations on recognized content.
Solution Approach 2:
The patent introduces an intermediary processing layer between OCR text recognition and the final output. This intermediary layer assigns context types (receipt, menu, form) and structures the recognized text into manipulatable data fields, serving as a mediator that enables users to perform context-aware operations without directly manipulating raw text.
2Adaptability or versatility
If general OCR text recognition is performed, then text identification is achieved, but context-specific manipulation capabilities (such as recalculating sales tax or obscuring sensitive information) are not provided
Solution Approach 1:
The patent performs preliminary context assignment and field structure organization immediately after text recognition. By pre-organizing the recognized content into context-specific data fields (items, prices, totals for receipts; dishes, prices for menus) before user interaction, the system reduces the complexity of subsequent manipulation operations and enables intuitive context-aware editing.
Solution Approach 2:
The patent implements a universal context assignment framework that can handle multiple document types (receipts, menus, forms) through a common processing architecture. The system assigns context types and applies appropriate field structures universally across different document formats, enabling consistent context-specific manipulation capabilities without requiring separate complex processing paths for each document type.
3Loss of information
If all recognized data fields are displayed in the output image, then complete information is provided, but sensitive information privacy is compromised
Solution Approach 1:
The patent applies local quality by allowing different display treatments for different data fields within the same document. Users can specify which fields should be displayed, modified, or obscured based on their sensitivity or relevance. This enables selective information disclosure where sensitive fields (such as personal information or payment details) can be obscured while maintaining the display of non-sensitive fields, thus preserving privacy without losing essential information.
Data Source
AI summary
Techniques for assigning context to a digitally captured image, and for manipulating recognized data fields within such image. In an exemplary embodiment, a context of an image may be assigned based on, e.g., user input or pattern recognition. Based on the assigned context, recognized data fields within the image may be manipulated according to context-specific processing. In an aspect, processing specific to a sales receipt context may automatically manipulate certain data, e.g., calculate updated sales tax and subtotals based on user-designated fields, and display the automatically calculated data in an output receipt. Fields not designated by the user may be selectively concealed in the output receipt for privacy. Further aspects disclose processing techniques specific to other contexts such as restaurant menu, store shelf, and fillable form contexts.