Composite Document Segmentation via Continuity Pattern Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing page stream segmentation methods fail when composite documents have similar text font, size, header, and footer information, requiring significant manual effort for separation.
Innovation Solution
A system using deep learning neural networks to analyze image and text features across consecutive pages, determining continuity patterns to categorize pages as belonging to the same document and automatically separate them.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional page stream segmentation methods based on structural data and character data are used, then documents with distinct structural characteristics can be separated, but documents with identical or similar text font, size, header, and footer information cannot be separated
Solution Approach 1:
The patent segments the document analysis into multiple independent feature dimensions: structural data (headers, footers, tables), character data (fonts, sizes), and layout data (margins, spacing, page orientation). By analyzing each dimension separately and combining results, the system can identify subtle differences that single-dimension methods miss, enabling separation of documents with similar overall characteristics.
Solution Approach 2:
The patent introduces layout data as an additional analytical dimension beyond traditional structural and character data. This includes analyzing whitespace distribution, element positioning, margin patterns, and spatial relationships. By adding this dimensional perspective, the system gains the ability to distinguish documents that appear similar in content and structure but differ in their spatial arrangement and formatting patterns.
2Reliability
If manual separation methods are used for composite documents, then accurate separation can be achieved, but significant time and effort are required
Solution Approach 1:
The patent implements self-service by training the machine learning model to automatically learn and identify document boundaries and characteristics from training data. The system performs feature extraction, pattern recognition, and document separation autonomously without requiring manual intervention for each document, thereby achieving both high accuracy and efficiency.
Solution Approach 2:
The patent performs preliminary action by pre-training the machine learning model with labeled composite document data before deployment. The model learns to recognize document patterns, structural features, and separation boundaries in advance, enabling it to rapidly and accurately separate new composite documents without requiring manual preprocessing or intervention during actual operation.
Data Source
AI summary
A system for obtaining documents from a composite file comprising a stream of multiple pages is provided. The system may comprise one or more processors configured to receive the composite file comprising the multiple pages and split the composite file to obtain individual pages of the composite file, wherein image of each of the individual pages and image vector for each of the individual pages from the image of the respective page may be obtained. The processor may further obtain text present in each of the individual pages and text vector for each of the individual pages from the text of the respective page. The processor may further determine continuity pattern between pages that are consecutive based on the image vector and the text vector of the consecutive pages and may categorize the consecutive pages as belonging to the same document in case the determined continuity pattern between the consecutive pages indicate that the consecutive pages belong to the same document.