• D. Muneendra
• C. Prudhvi
• E. Sathvika
• K. Sasank
• Shaik Shajahan

The guided filter and its later variations have been widely used in various image processing and computer vision applications, owing to its minimal complexity and good edge-preservation features. Despite this success, the guided filter's various variations are unable to handle increasingly aggressive filtering strengths, resulting in the appearance of "detail halos." At the same time, when the input and guide images ae same guided filter exhibit structural inconsistencies, these existing filters function poorly. the guided filter acting as a variable-strength locally isotropic filter on the image. The use of unweighted averaging in the final steps of guided filter variants such as the adaptive guided filter, weighted guided image filter, and gradient-domain guided image filter causes this behavior, according to our analysis. The Anisotropic Guided Filter (AnisGF) is a novel filter that uses weighted averaging to achieve maximum diffusion while maintaining strong edges in the image. The proposed weights are optimized based on local neighborhood variances to produce anisotropic filtering while maintaining the original guided filter's low computing cost. The proposed method of detail halos and the management of inconsistent structures found in previous guided filter variations, according to synthetic experiments. Furthermore, experiments with sand-dust image enhancement and strip-noise removal also show how the technique improves image quality.

Detail halos, Edge preservation, Isotropic guided filter, Adaptive guided filter, Weighted guided filter.

"Sand-Dust Image Enhancement and Infrared Strip-Noise Removal Using Anisotropic Guided Filter", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.g341-g344, April-2024, Available :http://www.jetir.org/papers/JETIR2404644.pdf

"Sand-Dust Image Enhancement and Infrared Strip-Noise Removal Using Anisotropic Guided Filter", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppg341-g344, April-2024, Available at : http://www.jetir.org/papers/JETIR2404644.pdf