ATM Magnetic Ink Character Recognition via Dual-Sensor Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated teller machines (ATMs) face challenges in accurately recognizing magnetic ink characters on checks due to reliance on high-resolution MICR sensors, which increase costs and complexity, while also risking reduced reliability in authenticating checks with potential counterfeit or damaged characters.
Innovation Solution
A method utilizing a contact image sensor for optical character recognition (OCR) and an MR sensor for character-based waveforms, combined with a waveform authentication algorithm, to compare and verify results, eliminating the need for a high-resolution MICR sensor, thereby simplifying the authentication unit and reducing manufacturing costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a high-resolution MICR sensor is used to read magnetic ink characters on checks, then the recognition accuracy of magnetic ink characters is improved, but the device complexity and manufacturing cost increase
Solution Approach 1:
The patent combines the functions of magnetic ink character recognition and bill authentication into a single authentication unit. The contact image sensor serves dual purposes: capturing check images for MICR character recognition and capturing bill images for authentication. This merging eliminates the need for separate high-resolution MICR sensors, reducing device complexity while maintaining recognition accuracy through software-based character extraction and verification algorithms.
Solution Approach 2:
The contact image sensor is designed to perform multiple functions: it captures images of both checks and bills, and the same sensor data is used for both MICR character recognition and bill authentication. This multi-functionality reduces the number of specialized sensors needed, simplifying the overall system architecture while maintaining high recognition accuracy through advanced image processing algorithms.
2Reliability
If a high-resolution MICR sensor is installed in the authentication unit, then the reliability of check authentication is improved, but the manufacturing cost increases
Solution Approach 1:
The patent uses the contact image sensor to capture images of magnetic ink characters, creating a digital copy of the MICR data. This digital copy is then processed through character recognition algorithms to extract and verify MICR information. By using imaging and software processing instead of specialized magnetic sensors, the system maintains authentication reliability while significantly reducing manufacturing costs associated with high-resolution MICR sensors.
Solution Approach 2:
The patent replaces the mechanical/magnetic sensing system (MICR sensor) with an optical imaging system (contact image sensor) combined with digital signal processing. The contact image sensor captures optical images of the magnetic ink characters, and software algorithms convert these images into recognizable character data. This substitution eliminates the need for expensive specialized sensors while maintaining authentication reliability through advanced image recognition and verification algorithms.
3Device complexity
If the authentication unit is simplified by removing the MICR sensor, then the manufacturing cost and device complexity are reduced, but the ability to accurately recognize magnetic ink characters deteriorates
Solution Approach 1:
The patent changes the operating parameters and processing methods of the contact image sensor to optimize it for MICR character recognition. The sensor uses specific imaging parameters (resolution, lighting, contact pressure) to capture clear images of magnetic ink characters. Advanced image processing algorithms then enhance these images, adjust contrast and sharpness, and apply character recognition patterns to accurately extract MICR data, achieving high recognition accuracy without requiring a dedicated MICR sensor.
Solution Approach 2:
The system implements feedback mechanisms where the captured images are processed through multiple stages of analysis. The character recognition algorithms compare extracted characters against expected MICR formats and patterns, and verification algorithms cross-check the recognized data. This multi-stage feedback process ensures high accuracy in magnetic ink character recognition even without specialized sensors, as errors can be detected and corrected through iterative verification.
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
Ensures accurate recognition of magnetic ink characters, maintaining reliability in check authentication without the need for a high-resolution MICR sensor, thus simplifying the ATM's configuration and reducing production costs.
Implementation Method 1
an image of a check that is acquired through a contact image sensor
Implementation Method 2
character-based waveforms of magnetic ink characters acquired from an MR sensor
Data Source
AI summary
Recognizing magnetic ink characters in an automated teller machine and, more particularly, recognizing magnetic ink characters in an automated teller machine. Results of optical character recognition (OCR) are compared based on an image acquired through a contact image sensor (CIS) provided in an authentication unit and character-based waveforms of magnetic ink characters acquired through an MR sensor. Whether a bill is legitimate is authenticated, and thus correct reading of magnetic ink characters printed on a check is realized. The structure of the authentication unit can be simplified so that correct recognition of the magnetic ink characters printed on the check in a normal automated teller machine is supported without a high-resolution MICR sensor, and the cost of manufacturing the automated teller machine can be effectively reduced.