Document Image Area Identification via Candidate Edge Sorting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional ID card automatic identification technologies face difficulties in recognizing characters from images obtained directly by photographing, rather than scanning, due to variations in shooting angle, background, and illumination conditions, which affect the detection of predefined edges and information areas.
Innovation Solution
A method and apparatus for identifying candidate predefined edges in a document image, sorting them to determine a target edge, and using this edge to accurately locate information areas such as name, date of birth, gender, and ID number regions, employing techniques like straight line detection, Sobel filtering, and histogram analysis to enhance edge detection and area identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ID card scanning is performed using a fixed relative position scanning device, then identification accuracy is improved, but device complexity and operational rigidity increase
Solution Approach 1:
The patent transforms the static fixed-position scanning approach into a dynamic image processing system that can adapt to various shooting angles and document positions. The method dynamically identifies candidate edges, determines target edges, and locates information areas through computational processing rather than mechanical positioning, thereby improving accessibility while maintaining identification accuracy through software-based adaptation.
2Ease of operation
If photographing is used to obtain document images, then ease of operation is improved, but measurement precision deteriorates due to variations in shooting angle, background, and illumination
Solution Approach 1:
The patent employs parameter changes by identifying multiple candidate edges and selecting the target edge based on specific criteria (such as position relationships with information areas). This approach adapts to varying illumination and shooting conditions by flexibly determining the most appropriate edge among candidates, thereby maintaining precision despite environmental variations.
Solution Approach 2:
The system performs preliminary edge detection to identify multiple candidate edges before determining the target edge. This preliminary action allows the system to pre-process the image data and prepare multiple options for edge selection, ensuring that the final target edge selection is robust against variations in shooting conditions.
3Measurement precision
If multiple candidate edges are identified and sorted to determine a target edge, then area identification accuracy is improved, but processing time increases
Solution Approach 1:
The patent identifies multiple candidate edges (excessive action) but only processes them to the extent necessary for accurate area identification. By sorting candidate edges and selecting the target edge based on position relationships with information areas, the system performs partial processing on the full set of candidates, achieving high accuracy without exhaustive analysis of all possible edges.
Data Source
AI summary
A method for area identification includes identifying a plurality of candidate predefined edges in a document image of a document. The candidate predefined edges are edges in a predefined direction of the document. The method further includes determining one of the candidate predefined edges to be a target predefined edge and identifying at least one information area in the document image based on the target predefined edge.