Sheet Identification via Area Weighting and Logical Combination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sheet identification methods struggle to reliably and efficiently identify local features in image patterns of sheets, such as paper sheets, while maintaining high-speed operation and robustness against variations in the medium, including printing concentration, skewing, and sliding.
Innovation Solution
A sheet identification apparatus and method that divides the image pattern into multiple areas, weights and selects these areas based on their differences and variations, and determines the identification result through a logical combination of identification results from each area, accounting for skew and sliding of the sheet.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the entire pattern area is uniformly processed to identify local features, then identification precision is improved, but calculation cost increases and processing speed decreases
Solution Approach 1:
The pattern area is divided into multiple sub-areas, and identification is performed separately for each sub-area. This segmentation allows the system to focus computational resources on local features without processing the entire pattern, thereby maintaining identification precision while reducing overall calculation cost and improving processing speed.
2Productivity
If random pixel selection is used to reduce calculation cost, then processing speed is improved, but reliability of detection decreases
Solution Approach 1:
Different sub-areas are assigned different weights based on their importance for identification. Critical areas that contain key identification features are given higher weights and processed with higher priority, while less critical areas receive lower weights. This ensures that detection reliability is maintained by focusing resources on the most important regions.
3Device complexity
If feed state variations are not compensated, then device complexity is reduced, but identification reliability decreases due to medium variations
Solution Approach 1:
The feed state is detected and compensated for before the actual identification process begins. By performing this preliminary correction, the system eliminates the influence of medium variations such as skewing and sliding, ensuring that subsequent identification operations are performed on corrected, accurate data without requiring complex real-time adjustment mechanisms.
Data Source
Figure 1
Figure 2
Figure 3~5
AI summary
The class of a sheet is efficiently estimated and a pattern identification process which is robust to a variation in the medium can be performed by dividing (1) an image pattern of the sheet into a plurality of areas (pixels or sets of pixels), weighting (3) and selecting (4) the areas, attaining the identification results for the respective areas and determining the identification result of the whole portion based (6) on a logical combination of the identification results. Particularly, since the area weighting and selecting process is performed based on a difference between the classes and a variation in the class, the calculation amount can be reduced and the identification performance which is higher than that of a method which uniformly processes the whole portion of the pattern can be attained.