Meter Reading System Automatic Type Determination

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing meter reading systems face challenges in accurately reading indications from diverse types of meters without prior registration, as they require manual association and preregistration of meter types, which is time-consuming and prone to errors.

Innovation Solution

A reading support system that includes a processing device with an extractor to identify numeral regions and a type determiner to automatically determine the meter type based on numeral region positions, allowing for accurate extraction and reading of meter indications without prior registration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual association and preregistration of meter types are used, then the system can read meter indications, but the process becomes time-consuming and prone to errors

Engineering Contradiction:

Improvereading accuracyVSAvoidtime-consuming registration

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system automatically determines meter types by analyzing the spatial relationships between numeral regions, scale regions, and pointer regions in captured images. The type determination unit classifies meters into different types (e.g., electric water meters, gas meters, electricity meters) based on the extracted positional relationships, eliminating the need for manual registration and enabling the system to adapt to various meter types autonomously.

Inventive Principle:

Principle #25Self-service

2Measurement precision

If manual association and preregistration of meter types are used, then the system can read meter indications, but the process becomes prone to errors

Engineering Contradiction:

Improvereading accuracyVSAvoiderror-prone registration

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent replaces the manual mechanical registration process with an automated image processing and pattern recognition system. The extraction unit identifies numeral regions, scale regions, and pointer regions through image analysis, while the type determination unit uses algorithmic classification based on spatial relationships to automatically determine meter types, thereby eliminating human error in the registration process.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If the system supports diverse types of meters, then the versatility improves, but the complexity of automatic type determination increases

Engineering Contradiction:

Improvesupport for diverse meter typesVSAvoidcomplexity of type determination

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system segments the meter image into distinct functional regions: numeral regions (containing numerical values), scale regions (containing measurement scales), and pointer regions (containing indicator pointers). By extracting and analyzing the spatial relationships between these segmented regions, the type determination unit can classify different meter types without requiring complex overall image analysis, thereby managing complexity while maintaining versatility.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11861893B2Reading support system and moving body

Publication Date: 2024.01.02 KK TOSHIBA

AI summary

According to one embodiment, a reading support system includes a processing device. The processing device includes an extractor and a type determiner. The extractor extracts a plurality of regions from a candidate region. The candidate region is a candidate of a region in which a meter is imaged. The regions respectively include a plurality of characters of the meter. The type determiner determines a type of the meter based on positions of the regions.