Automatic Meter Reading via Optical Character Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual reading of meters such as gas, electric, and water meters is inefficient, requiring physical access and observation at each meter location.
Innovation Solution
An automatic meter reading system captures images of the meter face and performs optical character recognition using stored templates to extract numerical values from digital displays, utilizing a camera and processor adapted from optical mouse technology to transmit readings remotely.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual reading of meters is performed, then reading accuracy can be ensured through direct observation, but reading efficiency is reduced due to physical access requirements
Solution Approach 1:
The patent replaces manual mechanical reading operations with an automated optical system. A camera captures images of the meter display, and an optical character recognition system processes these images to extract reading data automatically, eliminating the need for physical access and manual observation while maintaining reading accuracy
Solution Approach 2:
The system creates a digital copy of the meter display through image capture. The camera takes a photograph of the meter face, and the OCR system processes this digital copy to extract the reading, allowing remote and automated data collection without physical interaction with the meter
2Measurement precision
If optical character recognition is performed without templates, then system complexity is reduced, but reading accuracy decreases due to difficulty in detecting and measuring digit patterns
Solution Approach 1:
The system performs preliminary action by pre-storing template images of standard digit patterns in memory. When a meter reading is captured, the system compares the captured digit images against these pre-stored templates to accurately identify the displayed values, improving recognition accuracy through pattern matching
Solution Approach 2:
The system changes parameters by adjusting and normalizing the captured digit images before comparison with templates. This includes scaling, positioning, and enhancing the captured images to match the template format, thereby improving the accuracy of the optical character recognition process
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
Enables efficient and remote capture of meter readings, reducing manual intervention and allowing for frequent or scheduled data collection without physical access to the meters.
Implementation Method 1
An image on a face of the meter is captured
Implementation Method 2
Optical character recognition of digits of a digital display on the face of the meter is performed. At least one stored template is used to perform the optical character recognition of digits
Data Source
AI summary
A meter is read. An image on a face of the meter is captured. Optical character recognition of digits of a digital display on the face of the meter is performed. At least one stored template is used to perform the optical character recognition of digits.