Interest point detection methods have received increasing attention and are widely used in computer vision tasks such as image retrieval and 3D reconstruction. In this work, second-order anisotropic Gaussian directional derivative filters with multiple scales are used to smooth the input image and a novel blob detection method is proposed. Extensive experiments demonstrate the superiority of our proposed method over state-of-the-art benchmarks in terms of detection performance and robustness to affine transformations.

翻译：兴趣点检测方法日益受到关注，并广泛应用于图像检索和三维重建等计算机视觉任务中。本文采用多尺度的二阶各向异性高斯方向导数滤波器对输入图像进行平滑处理，并提出了一种新颖的斑点检测方法。大量实验表明，我们提出的方法在检测性能和对仿射变换的鲁棒性方面优于现有最先进的基准方法。