Document Image Extraction Using Visual Identifiers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Travelers and enterprises face inefficiencies in claiming Value-Added Tax (VAT) refunds due to complex foreign tax laws, manual processing of invoices, and the need for individual scanning, leading to wasted time and potential errors.
Innovation Solution
A method and system for extracting document images from multiple-document images using visual identifiers, analyzing these identifiers to identify and extract individual invoice images, and creating separate files for each, which can be processed electronically for VAT refunds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If individual invoices are scanned separately, then each invoice can be processed accurately, but the time and resources required increase significantly
Solution Approach 1:
The patent merges multiple individual invoice scanning operations into a single batch processing operation. The system captures multiple invoices simultaneously using a camera or scanner, processes them together through image processing algorithms to separate and identify each invoice, and generates individual files for all invoices in one workflow, thereby reducing total processing time while maintaining accuracy
Solution Approach 2:
The patent applies segmentation by automatically dividing a captured image containing multiple invoices into separate individual invoice images. The system uses image processing techniques to detect invoice boundaries, separate overlapping or adjacent invoices, and create distinct image files for each invoice, enabling accurate individual processing without manual separation
2Reliability
If manual processing of invoices is performed, then errors can be detected and corrected, but human error and time consumption increase
Solution Approach 1:
The patent replaces manual mechanical processing of invoices with an automated electronic system. The system uses optical character recognition (OCR), image processing, and pattern recognition algorithms to automatically extract, validate, and process invoice data, eliminating human error while maintaining high processing speeds and reliability through programmable validation rules
3Productivity
If multiple invoices are captured in a single image, then scanning efficiency improves, but the complexity of extracting individual invoices increases
Solution Approach 1:
The patent introduces intermediary processing steps between capturing multiple invoices and extracting individual ones. The system first performs preliminary image processing to enhance contrast, detect edges, and identify invoice regions, then uses these intermediate results to guide the separation and extraction of individual invoices, reducing the overall complexity of the extraction process
Data Source
AI summary
A system and method for extracting document images from images featuring multiple documents are presented. The method includes receiving a multiple-document image including a plurality of document images, wherein each document image is associated with a document; extracting a plurality of visual identifiers from the multiple-document image, wherein each visual identifier is associated with one of the plurality of document images; analyzing the plurality of visual identifiers to identify each document image; determining, based on the analysis, an image area of each document image; extracting each document image based on its image area.