Dawar Khan

About

Dawar Khan is a researcher focused on the critical challenge of robust fiducial marker design for Augmented Reality (AR) systems. His work centers on improving the reliability and recognition accuracy of markers used in applications ranging from robot navigation to interactive education. Khan’s major contributions target the widely-used ARToolKit library, where he has systematically addressed inter-marker confusion—a key barrier to seamless AR experiences. In his most cited work, "Classification of Markers in the ARToolKit Library to Reduce Inter-marker Confusion" (2014, 4 citations), he proposed a classification scheme to minimize tracking errors. He further advanced the field by investigating the optimal black-to-white ratio and information complexity for robust marker recognition (2014, 3 citations), and by developing a method for creating Sharp-Edged, De-noised, and Distinct (SDD) markers (2014, 3 citations). These contributions collectively enhance the visual distinctiveness and noise resilience of AR markers, directly improving system stability and user experience. Khan’s research provides foundational insights for anyone building reliable, marker-based AR systems, demonstrating a clear focus on practical, real-world performance optimization.

Research Focus

Key Achievements

Top Papers

1. 1
   Classification of Markers in the ARTool Kit Library to Reduce Inter-marker Confusion

   4 citations · 2014
2. 2
   Optimality of black to white ratio and information complexity for robust marker recognition

   3 citations · 2014
3. 3
   Sharp-Edged, De-noised, and Distinct (SDD) Marker Creation for ARToolKit

   3 citations · 2014

Key Collaborators

Contact & Links