【摘要】 针对电气设备红外图像边缘检测过程中伪边缘过多且易发生边缘断裂的问题，提出一种基于Canny算子的电气设备红外图像改进边缘检测算法。首先，采用Gamma变换对图像低灰度或高灰度部分的细节进行增强以使图像纹理和边缘更加明显；其次，采用插值方式进行非极大值抑制，确定最能吻合像素点所在梯度方向两侧的像素值，提高边缘定位准确性，改善边缘断裂的问题；最后，利用梯度强度计算法实现阈值自动选择，提升算法效率，保证边缘连续性。数据分析和算例验证结果表明，相比传统Canny边缘检测算法，该方法能更准确地检测边缘信息且提取的边缘具有更好的连通性。更多还原

【Abstract】 Aiming at the problem of too many false edges and easy edge breakage in the process of edge detection of infrared images of electrical equipment, an improved edge detection algorithm of infrared images of electrical equipment based on Canny operator is proposed. Firstly, Gamma transform is used to enhance the details of the low-gray or high-gray part of the image to make the image texture and edges more obvious.Interpolation method is used to suppress the non-maximum value, and the pixel values on both sides of the gradient direction that are most consistent with the pixel points are determined to improve the accuracy of edge positioning and improve the problem of edge fracture. Gradient intensity calculation method is used to achieve automatic threshold selection, improve the efficiency of the algorithm, and ensure the continuity of the edge.Finally, the data analysis and example verification results show that compared with the traditional Canny edge detection algorithm, the method proposed in this paper can detect the edge information more accurately and the extracted edges have better connectivity.更多还原