Edge detection as a pre-processing stage is a fundamental and important aspect of the number plate extraction system. This is due to the fact that the identification of a particular vehicle is achievable using the number plate because each number plate is unique to a vehicle. As such, the characters of a number plate system that differ in lines and shapes can be extracted using the principle of edge detection. This paper presents a method of number plate extraction using edge detection technique. Edges in number plates are identified with changes in the intensity of pixel values. Therefore, these edges are identified using a single based pixel or collection of pixel-based approach. The efficiency of these approaches of edge detection algorithms in number plate extraction in both noisy and clean environment are experimented. Experimental results are achieved in MATLAB 2017b using the Pratt Figure of Merit (PFOM) as a performance metric

翻译：边缘检测作为预处理阶段是车牌提取系统中基础且重要的一环。这是因为通过车牌可识别特定车辆，每个车牌对车辆具有唯一性。因此，通过边缘检测原理可提取出具有不同线条与形状特征的车牌字符。本文提出一种基于边缘检测技术的车牌提取方法。车牌边缘通过像素值强度的变化进行识别，因此采用单像素基础或像素集合方法进行边缘检测。实验研究了这些边缘检测算法在噪声环境与清洁环境中的车牌提取效率。基于MATLAB 2017b平台，采用Pratt品质因数（PFOM）作为性能指标进行实验验证。