Edge Direction Evaluation for Vehicle Number Plate Extraction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The increasing number of target vehicles in vehicle number recognition systems necessitates faster extraction of vehicle number plate regions to recognize vehicle numbers efficiently.

Innovation Solution

An image recognition device that evaluates edge directions by assigning points based on the deviation between the outline and edge directions, and extracts vehicle number plate regions using these points, with optional intensity and distribution totalization for precise extraction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional vehicle number plate extraction methods are used, then the recognition system can operate, but the extraction speed is insufficient to handle the increasing number of target vehicles

Engineering Contradiction:

Improveextraction speedVSAvoidtime for region extraction

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent replaces complex mechanical image processing systems with a simplified edge-direction-based algorithm. Instead of using traditional multi-step region extraction methods involving multiple image processing operations, the invention uses edge direction evaluation and point assignment to rapidly identify vehicle number plate regions, achieving high-speed extraction suitable for handling increasing numbers of target vehicles

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the extraction approach by focusing on edge direction parameters rather than traditional intensity or gradient-based parameters. By evaluating edge directions and assigning points based on deviation from character outlines, the system achieves faster processing while maintaining extraction accuracy, directly addressing the speed requirement for handling increasing vehicle numbers

Inventive Principle:

Principle #35Parameter changes

2Productivity

If faster extraction methods are implemented, then processing time is reduced, but extraction accuracy may deteriorate

Engineering Contradiction:

Improveextraction speedVSAvoidextraction accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent incorporates feedback mechanisms through edge direction evaluation and point assignment based on deviation amounts. The system continuously evaluates edge directions against character outline directions and adjusts point assignments accordingly, providing feedback that ensures accurate extraction while maintaining high processing speed

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent substitutes traditional slow and complex image processing mechanisms with a streamlined edge-direction-based system that achieves both speed and accuracy. By replacing multi-step processing with direct edge evaluation and point assignment, the system maintains precision while dramatically improving extraction speed

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS9747511B2Image recognition device, image recognition method, program, and recording medium

Publication Date: 2017.08.29 MITSUBISHI HEAVY IND MACHINERY SYST LTD

AI summary

An image recognition device includes an edge direction evaluation unit configured to evaluate a direction of an edge at each coordinate by assigning points to the coordinate when a deviation amount between a direction of an outline of an abundance ratio higher than a predetermined abundance ratio threshold value among directions of an outline of a character available for the vehicle number plate and the direction of the edge at each coordinate of the image is less than a predetermined deviation amount threshold value and a vehicle number plate region extraction unit configured to extract a region of the vehicle number plate from the image based on a distribution of the points assigned by the edge direction evaluation unit.