Among the common image structures, line feature is the extensively used geometric structure for various image processing applications, including the analysis of biomedical image with blood vessels highlighting, graph-shape structures, cracks detection, satellite images or remote sensing data. Multi-scale processing of line feature is essentially required for the extraction of more relevant information or line structures of heterogeneous widths. In this paper, a multi-scale filtering-based line detection approach using second-order semi-Gaussian anisotropic kernel is proposed. Meanwhile, a strategy is introduced to calculate the strength of the observed line feature across the different scales. The proposed technique is evaluated on real images by using their tied hand-labeled images. Finally, the experimental results and comparison of images containing different line feature widths with state-of-the-art techniques have sufficiently supported the effectiveness of our technique.