Client-Side Document Classification With OCR Region Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users often incorrectly identify or upload incorrect documents during the electronic document upload process, leading to delays and inconvenience in processing.
Innovation Solution
A method and system for real-time document classification on user equipment using optical character recognition (OCR) and machine learning algorithms to identify and classify document sections, allowing immediate correction of errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If document classification is performed on the server side after upload, then classification accuracy can be improved through comprehensive analysis, but processing time increases and user convenience deteriorates
Solution Approach 1:
The patent applies preliminary action by performing document classification on the client side before upload. The system extracts text from document images using OCR, classifies the document type locally using machine learning models, and prepares classification results in advance. This preliminary classification reduces server processing time and allows users to correct errors before submission, resolving the contradiction between accuracy and processing time.
2Reliability
If full document analysis is performed to ensure accurate classification, then classification reliability improves, but computational resources and processing time increase
Solution Approach 1:
The patent applies segmentation by dividing the document into multiple regions of interest based on contrast analysis. Instead of analyzing the entire document, the system identifies and processes only specific sections that contain classification-relevant text. This segmented approach maintains classification reliability while significantly reducing computational resources and processing time required for full document analysis.
3Speed
If client-side processing is implemented to reduce server load, then processing speed improves, but device complexity and energy consumption increase
Solution Approach 1:
The patent applies partial action by implementing only the essential components of document classification on the client side. The system performs OCR on selected document regions and uses pre-trained machine learning models for classification, rather than implementing complete document analysis capabilities. This partial implementation achieves faster processing speed while keeping client device complexity and energy consumption at acceptable levels.
Data Source
AI summary
A method for classifying a document in real-time is disclosed. The method includes identifying one or more sections of the document likely to contain text based on a contrast between dark space and light space in an image of the document. Optical character recognition is performed within the identified sections of the document to identify a set of words within each identified section of the document. The sets of words are extracted from the identified sections of the document, and a subset of the sets of words is selected for classifying the document based on a preconfigured option. The document is then classified by inputting the selected subset of words into one or more machine learning models. The method includes transmitting the document and the determined classification of the document to an external server.