Vehicle Number Identification Using Multi-Source Matching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current vehicle identification methods, such as reading number plates and acquiring information from in-vehicle devices or tags, often require significant human resources and data preparation, especially when combining different identification methods, and may fail to accurately identify vehicles, leading to inefficiencies and potential fraud.

Innovation Solution

A vehicle number identification device that combines registration number information, OCR processing, machine-learning models, and image analysis to accurately identify vehicles by acquiring and matching registration number information, OCR results, and machine-learning estimation results, reducing human resource burden and enhancing accuracy through automated data generation and fraud detection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If multiple identification methods (in-vehicle device reading and number plate recognition) are combined to improve vehicle identification accuracy, then identification reliability is improved, but the complexity of data preparation and human resource burden increases

Engineering Contradiction:

Improvevehicle identification accuracyVSAvoiddata preparation complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent combines multiple identification methods (in-vehicle device reading and number plate recognition) into a unified identification system. The determination unit integrates results from both methods to identify vehicles, improving reliability while managing complexity through automated processing.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system performs self-verification by comparing identification results from different methods automatically. The determination unit autonomously evaluates consistency between in-vehicle device readings and number plate recognition results without requiring manual intervention, reducing human resource burden.

Inventive Principle:

Principle #25Self-service

2Reliability

If multiple identification methods are combined to complement each other and ensure toll charging, then identification reliability is improved, but the operational complexity and human resource burden increase

Engineering Contradiction:

Improvevehicle identification accuracyVSAvoidoperational simplicity

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The determination unit autonomously evaluates and compares identification results from multiple methods without requiring manual operation. The system self-manages the complexity of coordinating multiple identification approaches, presenting a simplified interface for toll charging operations.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements feedback mechanisms where identification results from different methods are continuously compared and validated. The determination unit uses this feedback to automatically adjust and refine vehicle identification, reducing the need for manual operational intervention.

Inventive Principle:

Principle #23Feedback

3Ease of manufacture

If traditional OCR processing is used for number plate recognition, then implementation simplicity is maintained, but identification accuracy may be insufficient under varying conditions

Engineering Contradiction:

Improveimplementation simplicityVSAvoidnumber plate recognition accuracy

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent transforms the number plate image into feature vectors and inputs them into a trained neural network model. This parameter transformation from raw image data to extracted features enables more accurate recognition while maintaining implementation feasibility through pre-trained models.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system replaces traditional mechanical OCR processing with a machine learning-based neural network approach. This substitution improves recognition accuracy by leveraging learned patterns from training data while maintaining ease of implementation through automated model inference.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11875582B2Vehicle number identification device, vehicle number identification method, and program

Publication Date: 2024.01.16 MITSUBISHI HEAVY IND MACHINERY SYST LTD

AI summary

A vehicle number identification device includes a registration-number-information acquisition part configured to acquire registration number information associated with an identification media installed in a vehicle; a number-plate-image acquisition part configured to acquire a number-plate image of the vehicle; an OCR processing part configured to acquire OCR resultant information representing a result of an optical character recognition with respect to the number-plate image; an estimation processing part configured to input the number-plate image into a machine-learning model and to acquire estimation result information output from the machine-learning model; and a matching determination part configured to determine whether at least two types of information out of the registration number information, the OCR resultant information, and the estimation result information indicate a same vehicle number and to identify the same vehicle number as a vehicle number of the vehicle.