Seyed Mohammad Hosseini

Papers

Total Citations

H-Index

About

Seyed Mohammad Hosseini is a researcher specializing in computer vision and image processing, with a particular focus on edge-preserving smoothing techniques for range images. His major contribution lies in developing hybrid locally kernel-based weighted least square methods, which enhance the quality of 3D surface reconstructions by effectively reducing noise while maintaining sharp edges—a critical challenge in applications like autonomous navigation and medical imaging. His most-cited work, "Edge preserving range image smoothing using hybrid locally kernel-based weighted least square" (2022), has garnered 9 citations, reflecting its growing influence in the field. This paper introduces a novel approach that combines local kernel adaptation with weighted least squares optimization, achieving superior performance over traditional filters. Hosseini’s research bridges theoretical advancements with practical robustness, offering solutions that improve the reliability of depth sensors. His work is notable for its clarity and applicability, making it a valuable resource for students and engineers working on 3D data processing. As he continues to explore adaptive filtering and machine learning integration, Hosseini is poised to make further strides in enhancing the fidelity of visual data interpretation.