Papers
1
Total Citations
6
H-Index
1
About
Kanjar De is a researcher whose work sits at the intersection of computer vision, image quality assessment, and robotics. His primary research focus is on developing no-reference image quality metrics—methods that evaluate image sharpness and distortion without needing a pristine reference image. His most cited work, "No-reference Image Sharpness Measure using Discrete Cosine Transform Statistics and Multivariate Adaptive Regression Splines for Robotic Applications" (2018), introduces a novel approach that leverages DCT statistics and advanced regression techniques to quantify blur in images. This contribution is particularly valuable for autonomous systems, where real-time image quality assessment is critical for navigation, object recognition, and decision-making. With 6 citations, this paper has already influenced subsequent studies in robotic vision and computational imaging. De’s research addresses the growing challenge of managing vast volumes of digital visual data, offering practical solutions for enhancing the reliability of robotic perception. His work stands out for its application-driven approach, bridging theoretical image processing with real-world robotic needs, making him a notable contributor to the fields of computer vision and intelligent systems.
Research Focus
Key Achievements
Top Papers
- 1