Core Concepts
The study evaluates the effectiveness of edge detection algorithms in number plate extraction, emphasizing the importance of accurate identification for vehicle recognition.
Abstract
The study focuses on comparing different edge detection algorithms for number plate extraction, highlighting the challenges faced in noisy environments. It discusses the significance of edge detection as a pre-processing step and presents experimental results using MATLAB 2017b. The Pratt Figure of Merit (PFOM) is used as a performance metric to assess the accuracy of edges detected. Various existing edge detectors like Canny, Sobel, Prewitt, Laplacian, and Roberts are evaluated based on their performance in noisy and clean environments. The research suggests the need for enhanced noise filtering techniques and optimization methods to improve edge detection efficiency.
Stats
Experimental results are achieved in MATLAB 2017b using the Pratt Figure of Merit (PFOM) as a performance metric.
The Pratt Figure of Merit measures values between 0 and 1, with higher values indicating more accurate edge detection.
Quotes
"Noise intensity of 50% was added to the captured images in MATLAB 2017b with a view to depicting the worst-case scenario of noise level."
"The study compares different types of edge detection algorithms for number plate extraction."