Inclination Detection Using Shadow Boundary Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional electric skew correction techniques for automatic document feeders (ADFs) face challenges in accurately detecting document inclination due to variations in shadow width caused by document curls or folds, leading to erroneous correction and reduced accuracy in skew and registration correction, especially in high-density documents.
Innovation Solution
An inclination detecting device and method that utilize processing circuitry to detect boundaries between a background member and an object's shadow, and between the object and its shadow, to accurately determine the object's inclination by analyzing boundary groups across multiple detection positions in both main-scanning and sub-scanning directions, thereby improving correction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional electric skew correction techniques are used to detect document inclination, then the correction process can be performed, but the accuracy deteriorates due to variations in shadow width caused by document curls or folds
Solution Approach 1:
The patent segments the shadow boundary detection into multiple detection positions along the document outline. Instead of detecting a single boundary point, the system divides the shadow region into multiple segments and detects boundaries at each segment, then selects the most reliable detection results to calculate inclination, thereby reducing the impact of local variations caused by curls or folds
Solution Approach 2:
The patent performs detection at a plurality of detection positions beyond what would be minimally required. By detecting boundaries at multiple positions along the outline rather than a single position, the system obtains redundant measurement data that allows it to filter out erroneous detections caused by document deformations and select the most accurate readings
2Measurement precision
If shadow width variations are present due to document curls or folds, then the detection process becomes more complex, but the accuracy of inclination detection improves by using multiple boundary detection positions
Solution Approach 1:
The patent creates multiple copies of the boundary detection process at different positions along the document outline. By replicating the detection operation at multiple locations and then comparing the results, the system identifies consistent patterns that represent the true document inclination while filtering out anomalies caused by local deformations
Solution Approach 2:
The patent performs preliminary detection at multiple positions before final inclination calculation. The system first detects boundaries at all designated positions, then pre-processes these detections by identifying reliable ones and excluding erroneous ones, finally using the filtered results for accurate inclination and registration correction
Data Source
AI summary
An inclination detecting device includes processing circuitry. The processing circuitry is configured to detect, in image information that is an image of an object imaged by an imaging device at an imaging position where a background member forms a background, a first boundary between the background member and a shadow of the object at detection positions in at least one of main-scanning and sub-scanning directions on an outline of the object; detect a second boundary between the object and the shadow of the object at detection positions in at least one of the main-scanning and sub-scanning directions on the outline of the object in the image information; detect a boundary group including detection results of the second boundary at the detection positions; and detect an inclination of the object in the image information from detection results of the first boundary, the second boundary, and the boundary group.