By introducing curvilinear structures extraction (CSE) instead of watershed algorithm (WA) or nonmaximum suppression (NMS) to edge strength map (ESM), an improved ratio of exponentially weighted averages (ROEWA) edge detector with better capacity for weak edges detection is proposed to extract smooth edges and edge direction of synthetic aperture radar (SAR) images. Using the ROEWA, the ESM is calculated. Then the CSE algorithm is employed to extracted edges, by acquiring eigenvectors and eigenvalues of the Hessian matrix, the improved ESM (IESM) is obtained, which ensures the good weak edge detection capacity and smoothness of edges. Experimental results on simulated and real SAR images show that the improved ROEWA based on CSE attains better performance than the one using WA or NMS.

中文翻译：

---

基于曲线结构提取的改进ROEWA SAR图像边缘检测器

通过将曲线结构提取（CSE）代替分水岭算法（WA）或非极大值抑制（NMS）引入边缘强度图（ESM），提出了一种具有更好弱边缘检测能力的改进指数加权平均（ROEWA）边缘检测器提取合成孔径雷达（SAR）图像的平滑边缘和边缘方向。使用 ROEWA，计算 ESM。然后采用CSE算法提取边缘，通过获取Hessian矩阵的特征向量和特征值，得到改进的ESM（IESM），保证了良好的弱边缘检测能力和边缘平滑度。在模拟和真实 SAR 图像上的实验结果表明，基于 CSE 的改进 ROEWA 比使用 WA 或 NMS 获得更好的性能。