Document Reading Device Dual-Surface Cropping Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing document reading devices face challenges in accurately cropping documents when the document edges are not clearly represented in the image data, particularly when the background and document colors are similar, leading to failed detection and inaccurate cropping.
Innovation Solution
A document reading device that conveys a document along a path and reads both surfaces using larger read areas, with a region detector and cropping processor to identify and crop document regions based on successful detection results from either surface, ensuring accurate extraction even when edges are not clearly visible.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If document edges are detected in image data to accurately crop document portions, then cropping accuracy is improved, but detection reliability deteriorates when document and background colors are similar
Solution Approach 1:
The patent transitions from single-surface detection to dual-surface detection by adding the back surface reading dimension. The back surface reader reads the back surface of the document, and the region detector detects document regions on both front and back surfaces. This dimensional expansion provides alternative detection opportunities when front surface detection fails due to color similarity with the background.
Solution Approach 2:
The patent changes the detection parameter by switching from reading only the front surface to reading both front and back surfaces. When the document color is similar to the background color on the front surface, the detection system switches to utilize the back surface image data, where the document color contrasts with the opposing plate color, thereby maintaining detection reliability and cropping accuracy.
2Device complexity
If only front surface reading is performed, then device complexity is reduced, but cropping reliability deteriorates when edges are not clearly represented
Solution Approach 1:
The patent adds the back surface reading dimension by incorporating a back surface reader that reads the back surface of the document during conveyance. This dual-surface reading approach ensures that at least one surface provides detectable edges for accurate cropping, even when the front surface edges are not clearly represented due to color similarity with the background.
Solution Approach 2:
The patent performs preliminary reading of both front and back surfaces during document conveyance before the cropping operation. The region detector identifies document regions on either surface in advance, ensuring that reliable detection data is available before the cropping processor executes the cropping operation, thereby guaranteeing cropping reliability.
3Reliability
If dual surface reading is implemented, then detection reliability is improved, but device complexity increases
Solution Approach 1:
The patent merges the front surface reading and back surface reading operations into a single integrated document conveyance process. The document is conveyed along a conveyance path, and both surfaces are read during this single conveyance operation, rather than requiring separate reading operations. This merging approach improves detection reliability while minimizing the increase in device complexity.
Solution Approach 2:
The reading system is designed with multi-functionality to read both front and back surfaces of the document using the same conveyance mechanism. The region detector and cropping processor are configured to handle image data from either surface, making the system universally capable of detecting document regions regardless of which surface provides better edge contrast.
4Loss of time
If cropping is performed based on single surface detection, then processing time is reduced, but cropping accuracy deteriorates when detection fails
Solution Approach 1:
The patent performs preliminary detection of document regions on both front and back surfaces during the document conveyance process. The region detector identifies detectable document regions on either surface before the cropping operation begins. This preliminary action ensures that accurate cropping can be performed without requiring additional processing time for retrying failed detections.
Solution Approach 2:
The system uses the back surface image data to supplement front surface detection automatically. When front surface detection fails or provides insufficient information, the region detector self-service by utilizing the back surface image data that was already captured during conveyance, without requiring additional reading operations or extending processing time.
Data Source
AI summary
A document reading device includes a document conveyer, a first reader reading, in a first reading position, a first surface of a conveyed document such that a read area is larger than the conveyed document, a second reader reading, in a second reading position, a surface (second surface) opposite to the first surface such that a read area is larger than the conveyed document, a region detector executing a process of detecting a first document region that is a region of a document in first document image data and a process of detecting a second document region that is a region of the document in second document image data, and a cropping processor cropping a document portion on the first surface as first cropped image data and cropping a document portion on the second surface as second cropped image data, based on one of the document regions successfully detected.