Document Layout Approximation via Text and Avoidance Regions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies cannot convert physical documents with mixed text and non-text content into computer-searchable formats effectively, as they lack efficient methods to preserve the original layout and allow for interactive editing or selection of content.
Innovation Solution
A system and method that extracts text and non-text blocks from physical documents using OCR and handwriting recognition, generates a layout rectangle for text blocks, an avoidance region for non-text blocks, and iteratively adjusts text point size to create a searchable content layout, allowing for interactive editing and selection of content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If OCR and handwriting recognition are used to convert physical documents into computer-searchable formats, then searchable content is generated, but the original layout and visual structure are lost
Solution Approach 1:
The patent segments the document into distinct content blocks (text blocks and non-text blocks) with bounding boxes, then processes each segment separately to preserve layout information. This segmentation allows the system to maintain spatial relationships and structural details while converting content to machine-readable format.
Solution Approach 2:
The patent creates a digital copy of the physical document's layout structure by extracting bounding box information and content block positions. This copy preserves the original document's visual structure and spatial arrangement, enabling reproduction of layout information in the electronic version.
2Adaptability or versatility
If text blocks are extracted and converted to machine-encoded text, then searchable content is created, but non-text content like images and charts cannot be processed
Solution Approach 1:
The patent implements a universal processing framework that handles multiple content types (text blocks, non-text blocks, images, charts) within a single system. The same extraction and layout generation process applies to all content block types, making the system versatile and adaptable to various document formats.
3Manufacturing precision
If the layout rectangle and avoidance region are used to generate draft layout, then text placement is constrained, but iterative adjustment of point size is required
Solution Approach 1:
The patent employs an iterative process where the draft layout is generated and then adjusted through feedback loops. The system evaluates the layout against the layout rectangle and avoidance region constraints, making incremental adjustments to point size and text placement to achieve optimal layout accuracy.
Data Source
AI summary
An image processing method to generate a layout of searchable content from a physical document. The method includes generating extracted content blocks in the physical document, generating, based on a bounding box of a text block, a layout rectangle that identifies where machine-encoded text is placed in the layout of the searchable content, generating, based on a bounding box of a non-text block, an avoidance region that identifies where the machine-encoded text is prohibited in the layout of the searchable content, generating, based on the layout rectangle and the avoidance region, a draft layout of the searchable content, and iteratively adjusting a point size of the machine-encoded text in the draft layout to generate the layout of the searchable content.