Document Processing System Using Text Row Structure Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional methods for processing documents, such as optical character recognition and image registration, are time-consuming and processor-intensive, requiring significant storage and processing power, and often need prior knowledge of data location, making them ineffective for efficient document processing.

Innovation Solution

The system analyzes the physical structure of text rows in a document image by creating character blocks, determining their alignments, and classifying text rows based on these structures, using pattern matching to group similar rows and interpolate vector data for efficient document processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If optical character recognition is performed on the entire page, then text identification is achieved, but processing time and processor intensity increase significantly

Engineering Contradiction:
Improvetext identification accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent divides the document processing into distinct segments: first analyzing the physical structure of text rows and character blocks to identify document layout patterns, then using these patterns to guide selective OCR processing only on relevant regions. This segmentation avoids applying OCR to the entire page, thereby reducing processing time while maintaining text identification accuracy.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary analysis of the document's physical structure, including text row positions, character block alignments, and column formations, before conducting OCR. This preliminary structuring creates a framework that enables subsequent targeted text extraction without requiring full-page OCR, thus reducing processing time while preserving identification accuracy.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If image registration is used to compare documents, then document differences are identified, but storage requirements and processing power increase significantly

Engineering Contradiction:
Improvedocument comparison accuracyVSAvoidstorage requirements
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent extracts only the essential structural features from document images, such as text row positions, character block alignments, and column patterns, rather than storing and processing complete document images. This extraction approach enables document comparison and difference identification while dramatically reducing storage requirements compared to traditional image registration methods.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent creates simplified structural representations (copies) of document layouts using binary data to represent text row positions and character block alignments. These lightweight structural copies enable efficient document comparison without requiring storage of large image files, thus reducing storage requirements while maintaining comparison accuracy.

Inventive Principle:
Principle #26Copying

3Productivity

If conventional document processing methods are used, then document analysis is performed, but prior knowledge of data location is required

Engineering Contradiction:
Improvedocument processing efficiencyVSAvoidprocessing system complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent enables the processing system to automatically analyze and determine the physical structure of documents, including text row positions and character block alignments, without requiring external input about data locations. The system self-generates the structural framework needed for processing, eliminating the need for prior knowledge of data locations while maintaining processing efficiency.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent performs preliminary automatic analysis of document physical structure, creating a framework of text rows and character blocks that identifies data locations without requiring prior knowledge. This preliminary structuring action enables subsequent processing steps to proceed efficiently with automatically determined data locations, reducing system complexity.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS8214733B2Automatic forms processing systems and methods
Publication Date: 2012.07.03 HYLAND SWITZERLAND SARL

AI summary

Systems and methods analyze the physical structure of text rows in a document image, including the positions of one or more alignments of one or more character blocks in one or more text rows of the document image. The systems and methods determine one or more groups of text rows that are placed into a class based on the structures of the text rows, such as the positions of the one or more alignments of the one or more character blocks in each text row. A pattern matching system then determines if one or more classes should be further combined into a combined class.