基于改进Canny算法的复合绝缘子憎水性检测

Hydrophobic Detection of Composite Insulators Based on Improved Canny Algorithm

针对传统Canny算法的客观缺陷,提出一种基于改进Canny算法的复合绝缘子憎水性检测方法。联合小波去噪和多尺度Retinex处理方法实现对复合绝缘子表面液滴图像灰度分布的改善;运用Sobel算子计算梯度幅值;采用二维自适应类间方差完成憎水性图像的水珠轮廓分割;最后根据最大面积比法判断复合绝缘子憎水性等级。实验结果表明,利用该方法进行去噪处理可以抑制背景对水珠的干扰,有效地提取水珠(或水迹)的形状信息,增强复合绝缘子的图像分析效果,准确地识别HC_1～HC_3级憎水性的复合绝缘子。

Aiming at the objective flaws of the traditional Canny algorithm,an improved Canny algorithm is proposed for the hydrophobic detection of composite insulators.The process includes four aspects in detail:firstly,the grayscale distribution of droplet image of composite insulator surface is improved through multi-scale Retinex and wavelet denois ing;then,the gradient amplitude is calculated by Sobel operator;and the droplet profiles of hydrophobic images are split through 2-D Ostu algorithm;finally,the largest area ratio algorithm is utilized to determine the hydrophobic grade of insulators.The experimental results show that the method can effectively suppress the interference from background noise and extract the shape information of droplets(or watermarks)through the denoising processing,which enhances the image analysis effect of composite insulators and helps to accurately distinguish the hydrophobic grade of composite insulators within HC1~HC3.