Document Boundary Detection Using Visible and Invisible Light
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing devices that process images of documents using light beams of different wavelengths increase costs and man-hours due to the complexity of image data processing.
Innovation Solution
An image processing device that uses a light source to irradiate a document with both visible and invisible light, employing a white reference plate to absorb invisible light and detect document boundaries in both visible and invisible images, calculating detection results and errors to select the most accurate tilt detection result.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If image data is processed using light beams of different wavelengths, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent divides the image processing into separate stages: visible light image processing and invisible light image processing. Each stage handles specific wavelength data independently, with dedicated processing circuits for each type, thereby improving measurement precision through specialized processing while managing device complexity through functional segmentation.
Solution Approach 2:
The patent introduces a reference plate as an intermediary element that reflects invisible light. This reference plate serves as a mediator between the invisible light source and the image sensor, enabling the detection of document skew through invisible light without requiring complex direct measurement systems.
2Measurement precision
If multiple wavelengths are used for image processing, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The patent performs preliminary processing by detecting document boundaries and skew in visible light images first, then uses this information to guide subsequent invisible light image processing. This preliminary action reduces the overall processing time while maintaining high measurement precision through multi-wavelength analysis.
Solution Approach 2:
The patent applies partial processing by focusing invisible light processing only on regions identified as document areas through visible light imaging. Rather than processing the entire image at full resolution, the system applies invisible light analysis selectively to relevant portions, reducing processing time while maintaining accuracy.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach allows for efficient and cost-effective skew detection in documents using both visible and invisible light, reducing processing complexity and costs while maintaining accuracy.
Implementation Method 1
The white reference plate is disposed behind the document to absorb the invisible light
Implementation Method 2
The document reflects the light
Data Source
AI summary
In an image processing device, an image capturing section receives light reflected by a document, captures an image of the document with the light, and generates read data of the image. The light includes visible light and invisible light. The image includes a visible image and an invisible image. A first image processing circuit detects coordinates of first points on a boundary between the document and a white reference plate in the visible image and coordinates of second points on the boundary in the invisible image, calculates a first detection result, first detection error information, a second detection result, and second detection error information, and selects the first or second detection result based on the first and second error information. The calculation of the first detection result and the first error information and the calculation of the second detection result and the second error information are sequentially performed.