License Plate Recognition via Segmentation and Syntax Rectification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional license plate recognition technologies face challenges in accuracy due to complex backgrounds, varying illumination, and noise, leading to unstable binarized data and reduced recognition performance, especially when the license plate occupies a small area in images.
Innovation Solution
A system and method comprising an image capturing module, license plate detection module, segment extraction module, character classification module, and optional temporal rectification module, which captures images, identifies and extracts character segments, computes character probabilities, and rectifies characters based on syntax rules and binary thresholding techniques to improve recognition accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional binarization and histogram projection methods are used for license plate recognition, then the recognition process is simple and fast, but the recognition accuracy deteriorates due to noise and contamination in the binarized data
Solution Approach 1:
The patent segments the license plate image into multiple character-related data pieces using histogram projection, then processes each segment individually through template matching and classification. This segmentation allows the system to handle noise in each small region more effectively while maintaining overall recognition speed.
Solution Approach 2:
The patent introduces an intermediary template matching step between binarization and final classification. Templates serve as intermediaries to bridge the gap between noisy binarized data and character recognition, improving accuracy by comparing against known character patterns before final classification.
2Area of stationary object
If the license plate occupies a small area in the image, then the system can process distant vehicles, but the binarized data becomes unstable and recognition becomes difficult
Solution Approach 1:
The patent performs preliminary template matching and probability computation on each character segment before final classification. This preliminary action on small character segments allows the system to stabilize the binarized data even when the overall license plate occupies a small image area, by processing characters individually with enhanced detail.
3Measurement precision
If multiple character classification methods are used to improve accuracy, then the recognition precision improves, but the computational complexity and processing time increase
Solution Approach 1:
The patent applies template matching and probability computation to each character segment, which is a partial action applied locally to small regions. This approach achieves high precision through multiple classification methods without requiring the entire system to be overly complex, as each local segment is processed independently with optimized algorithms.
Data Source
AI summary
A license plate recognition system includes an image capturing module, a license plate detection module, a segment extraction module, a character classification module, and a character recognition module. The image capturing module is for capturing an image. The license plate detection module is for receiving the image and to identify a license plate in the image. The segment extraction module is for extracting a sequence of character segments on the license plate. The character classification module is for computing a probability of each possible character in each character segment. The character recognition module is for identifying permissible characters for the each character segment according to a syntax of the sequence of character segments, and to identify a character having a highest probability among the permissible characters as a selected character for the each character segment.