Mobile Device Text Area Capture via Image Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for capturing text areas on identification documents, such as machine-readable zones, are inefficient due to manual alignment requirements and increased recording time, especially in mobile device applications.

Innovation Solution

A mobile device equipped with an image camera and processor that captures and processes identification document images to segment, filter, and recognize text areas using techniques like Delaunay triangulation and optical character recognition, allowing for automatic detection and alignment correction without manual intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual alignment of identification documents with mobile devices is performed, then text area capture accuracy is improved, but recording time increases and efficiency decreases

Engineering Contradiction:
Improvetext area capture accuracyVSAvoidrecording time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs self-alignment by automatically detecting the document orientation and text area position through image processing algorithms. The mobile device captures the document image, segments it to identify text regions, and automatically adjusts the capture parameters without requiring manual user intervention for alignment, thus resolving the contradiction between accuracy and time consumption

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system performs preliminary image capture and analysis to detect document orientation and text area position before final processing. By pre-segmenting the image and identifying text regions in advance, the system prepares the data structure needed for accurate capture without requiring time-consuming manual alignment during the actual recording process

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If manual actions are performed by user for text area capture, then alignment accuracy is improved, but productivity decreases

Engineering Contradiction:
Improvealignment accuracyVSAvoidrecording efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system replaces manual mechanical alignment operations with automated image processing and computer vision algorithms. The processor automatically detects document boundaries, determines text area positions, and performs orientation correction through software-based image segmentation and analysis, eliminating the need for manual positioning while maintaining high accuracy

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-alignment by automatically detecting the document orientation and text area position through image processing algorithms. The mobile device captures the document image, segments it to identify text regions, and automatically adjusts the capture parameters without requiring manual user intervention for alignment, thus resolving the contradiction between accuracy and time consumption

Inventive Principle:
Principle #25Self-service

3Stability of the object's composition

If stationary capture devices are used for text area recording, then capture stability is improved, but device mobility and operational flexibility are reduced

Engineering Contradiction:
Improvecapture stabilityVSAvoiddevice mobility
Core Design Contradiction:
Stability of the object's compositionVSAdaptability or versatility

Solution Approach 1:

The system transitions from static stationary capture devices to dynamic mobile capture capabilities. The mobile device can be moved to different positions and angles while the image processing algorithms dynamically adjust to maintain stable and accurate text area capture, enabling both mobility and operational flexibility without sacrificing capture stability

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3259703B1Mobile device for capturing a text range on an identification document
Publication Date: 2020.11.11 BUNDESDRUCKEREI GMBH
  • EP3259703B1 patent drawingFigure 1
  • EP3259703B1 patent drawingFigure 2
  • EP3259703B1 patent drawingFigure 3

AI summary

The invention relates to a mobile device (100) for capturing a text range on an identification document, wherein the text range has a plurality of text characters in a predetermined arrangement in accordance with a predetermined arrangement extent, having a photographic camera (101), which is designed to capture an image of the identification document in order to obtain a document image, and a processor (103), which is designed to segment the document image in order to obtain a plurality of image segments, to select a plurality of text character image segments from the plurality of image segments, wherein the text character image segments each represent a text character, to determine a plurality of text character groups on the basis of the plurality of text character image segments, wherein the text character groups each comprise a series of text character image segments, and to compare a plurality of arrangement extents for the plurality of text character groups with the predetermined arrangement extent in order to capture the text range on the identification document.