Structured Document Authentication via Intermediary Reference Image
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for analyzing the visual inspection zone of structured personal documents are inefficient, prone to errors, and require prior knowledge of the document structure, leading to unreliable authentication, especially when images are of poor quality or perspective, and lack sufficient reference images for comparison.
Innovation Solution
A method that determines a character string from the automatic reading zone, generates an intermediate image, detects and locates a matching character string in the visual inspection zone, and identifies a region of interest, allowing for reliable analysis without prior knowledge of the document structure or reference images, using techniques like font detection and transcoding to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If character recognition (OCR) is performed in both MRZ and visual inspection zone with comparison, then authentication capability is improved, but error rate increases due to image quality issues and perspective distortion
Solution Approach 1:
The patent introduces an intermediary reference image containing standardized field labels that serves as a mediator between the acquired document image and the authentication process. This reference image provides stable, pre-defined regions that guide the OCR process, reducing errors caused by image quality and perspective issues while maintaining authentication reliability
Solution Approach 2:
The patent performs preliminary actions by pre-defining regions of interest and field labels in a reference image before the actual authentication process. This preliminary structuring of expected text locations and formats enables more accurate OCR by providing context and constraints, thereby improving measurement precision without sacrificing authentication reliability
2Loss of information
If analysis of visual inspection zone is performed to locate characters and understand their meaning, then information extraction capability is improved, but system complexity increases
Solution Approach 1:
The patent segments the document analysis task into distinct components: locating standardized field labels using the reference image, extracting personal information in designated regions, and processing different zones separately. This segmentation reduces system complexity by breaking down the complex analysis task into manageable, independent steps while maintaining complete information extraction
Solution Approach 2:
The patent creates a universal reference image structure that can be applied to multiple document types and languages. The standardized field labels and region definitions serve multiple purposes: guiding OCR, validating information presence, and structuring output. This multi-functionality reduces system complexity by providing a single reusable framework rather than separate processing logic for each document type
3Measurement precision
If reference images are stored in database for comparison, then authentication accuracy is improved, but device complexity and storage requirements increase
Solution Approach 1:
The patent uses a simplified copy of the document structure in the form of a reference image containing only standardized field labels and region definitions, rather than storing multiple complete reference images of actual documents. This copying approach maintains authentication accuracy by preserving the structural information needed for comparison while significantly reducing database complexity and storage requirements
Data Source
AI summary
A method for processing an acquired image (IA) showing a structured personal document (D) including a visual inspection zone (VIZ). The method includes determination of a first character string from an automatic reading zone or of barcode type (MRZ) of predetermined format, the first character string representing personalised information specific to the owner of the document (D), generation from the first character string of an intermediate image (IS) showing a second character string representing the same personalised information, detection in the acquired image of a third character string in the visual inspection zone (VIZ), representing the same personalised information, the detection comprising an overall comparison of the intermediate image (IS) with the acquired image, location in the visual inspection zone (VIZ) of a region of interest containing the third character string.