Continuous Edge-Shadow Detection for High-Speed Document Sizing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing document reading apparatuses struggle to accurately detect document size due to vague shadows at document edges, especially when high-speed reading is required, leading to potential inaccuracies in image output.
Innovation Solution
The apparatus employs a document size detector that uses a possible document edge detector to identify density-changing points and pixel groups in image data, ensuring the detected edge is a single continuous image in the main scanning direction, and adjusts light ratios to enhance shadow recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If high-speed reading is performed, then reading speed is improved, but shadow clarity deteriorates leading to inaccurate document size detection
Solution Approach 1:
The patent segments the shadow detection process into multiple discrete steps: (1) detecting density-changing points where image density meets a threshold, (2) identifying continuous pixel groups in the main scanning direction, (3) selecting the most downstream position in transport direction, and (4) verifying single-image continuity. This segmentation allows accurate document size detection even at high reading speeds by processing shadow information in structured stages rather than as a single operation.
Solution Approach 2:
The patent applies local quality by focusing detection resources on specific critical regions: the document edge shadow area and continuous pixel groups in the main scanning direction. By concentrating analysis on these locally significant features rather than processing the entire image uniformly, the system maintains detection accuracy at high reading speeds where comprehensive processing would be too slow.
2Device complexity
If shadow detection is used for document edge identification, then device simplicity is improved, but detection reliability deteriorates due to vague shadows
Solution Approach 1:
The patent changes detection parameters by introducing specific criteria: density threshold values to identify density-changing points, continuity requirements for pixel groups in the main scanning direction, and position verification in the transport direction. These parameter changes transform the vague shadow detection into a reliable measurement system while maintaining relative simplicity, avoiding the need for complex additional hardware.
Solution Approach 2:
The patent implements feedback by using the detected continuous pixel group information to verify and refine document edge identification. The system checks whether pixel groups form a single continuous image extending in the main scanning direction at the same transport position, and uses this feedback to confirm accurate document size detection, creating a self-verifying detection system.
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 ensures accurate detection of document size by maintaining a clear shadow representation, preventing split edges and enhancing precision in high-speed reading scenarios.
Implementation Method 1
emit light to a document to detect a shadow formed at the document edge
Data Source
AI summary
A document reading apparatus includes a possible document edge detector that detects, on the basis of a density change indicated by image data acquired by a reading device, a density-changing point, where image density is equal to or higher than a threshold, and most downstream in a transport direction, at each of positions in a main scanning direction, as a possible position of a document edge, and detects an image formed of pixels continuously aligned in the main scanning direction at the possible position, as a possible document edge, and a document size detector that detects a document size in the main scanning direction, on a basis of the image of the possible document edge, when the image of the possible document edge detected by the possible document edge detector is formed of a single image extending in the main scanning direction at a same position in the transport direction.