Structure-Preserving Image Smoothing using Adaptive Bilateral Filter
Riya Ruhela, Subir Singh Lamba, Bhupendra Gupta · 2023
Structure-preserving image smoothing is an important image processing problem that plays significant role in many applications of image processing and computer vision such as detail enhancement, edge detection, tone mapping, image segmentation, and image abstraction. We suggest a structure-aware bilateral filter to accomplish smoothing on an image without altering the salient structure information. The main contribution of the proposed work is the designing of the scale map, which has been used to choose the size of the spatial kernel at each pixel in accordance with the structure information. The aim behind using the scale map is to perform filtering on the homogeneous and texture regions while preventing filtering on the prominent structure regions. The proposed method has excellent structure-preserving and texture removal properties. The qualitative and quantitative analysis of the experimental results has shown the outperformance of the proposed method over the existing state-of-the-art methods.