Double Feed Detection Using Two-Run Ultrasonic and MICR Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Check processing systems face challenges in accurately distinguishing between true double feeds and false positives/negatives, leading to delays and financial losses due to operator errors and the inability to automatically detect carrier envelopes.
Innovation Solution
Implementing a two-run system where all potential double feeds are initially rejected, followed by a second run for manual evaluation, using MICR, OCR, and ultrasonic detection to differentiate between carrier envelopes and true double feeds, and applying distance functions to compare recognition data from both runs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ultrasonic double feed detection is used to detect potential double feeds, then double feed detection capability is improved, but carrier envelopes are incorrectly identified as double feeds causing false positives
Solution Approach 1:
The detection process is divided into two separate runs: first run uses ultrasonic detection to identify potential double feeds, second run uses MICR/OCR to verify carrier envelopes. This segmentation allows each detection method to specialize in its strength without interference from the other method's weaknesses.
Solution Approach 2:
A two-run verification system acts as an intermediary between ultrasonic detection and final double feed determination. The first run identifies candidates, the second run verifies them using different detection methods, and the system reconciles the results to eliminate false positives while maintaining true positive detection.
2Measurement precision
If operators manually evaluate all potential double feeds, then detection accuracy is improved, but processing time increases significantly causing delays
Solution Approach 1:
Instead of requiring full manual evaluation of all potential double feeds, the system performs partial automated verification using a second run with MICR/OCR detection. This partial automation handles the verification task for most items, reserving manual intervention only for cases where automated methods are inconclusive, thus reducing overall processing time while maintaining accuracy.
Solution Approach 2:
The system performs self-verification by automatically running a second detection pass through the same items identified as potential double feeds. This self-service approach allows the system to verify its own detections without requiring immediate human intervention, significantly reducing processing time while maintaining high accuracy.
3Productivity
If all potential double feeds are automatically rejected in the first run, then processing speed is improved, but true double feeds may be missed causing false negatives
Solution Approach 1:
The first run performs preliminary identification of potential double feeds using ultrasonic detection, quickly filtering candidates before more thorough verification. This preliminary action maintains processing speed by handling the bulk of items rapidly, while the second run provides thorough verification to eliminate false negatives, combining speed and reliability.
Solution Approach 2:
The system uses feedback from the first run to guide the second run. Items identified as potential double feeds in the first run are fed back into the second run for verification. This feedback loop ensures that items requiring further scrutiny receive it, while allowing the majority of items to proceed quickly through the first run, maintaining both speed and reliability.
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 reduces human intervention, minimizes errors, and ensures accurate detection of true double feeds, thereby reducing delays and financial losses by automating the initial rejection process and allowing carrier envelopes to pass correctly.
Implementation Method 1
double feed detection may include pattern matching, such as by using a pre-encoded MICR string to detect carrier items, to check for blank MICR, or using Optical Character Recognition (OCR) from an original item in the see-through window of the carrier envelope
Implementation Method 2
double feed detection may include pattern matching, such as by using a pre-encoded MICR string to detect carrier items
Implementation Method 3
using Optical Character Recognition (OCR) from an original item in the see-through window of the carrier envelope
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
Examples of a system and method for identifying double feed documents are generally described. A method (400) may include scanning a plurality of documents using a scanner in a first configuration (402) and rejecting identified potential double feeds of checks from the plurality of checks in the first configuration (404). The method may include rescanning identified potential double feeds in a second configuration (406).