A Novel Augmented Reality Approach in Oral and Maxillofacial Surgery: Super-Imposition Based on Modified Rigid and Non-Rigid Iterative Closest Point

Abstract

Background: This paper aim to improve the accuracy of super-imposition and processing time during Oral and Maxillofacial surgery. Methodology: The proposed system consists of Enhanced Tracking Learning Detection (TLD) enhance by an occlusion removal algorithm to remove occlusion in the region of interest. In addition, we propose a Modified Rigid and Non-Rigid Iterative Closest Point (MRaNRICP) for pose refinement. Moreover, this proposed MRaNRICP having a new error metric Boolean function to dictate the Iterative Closest Point (ICP)’s stopping condition. Results: The proposed system using a new error metric being defined as a new MRaNRICP and it gave overlay error from 0.22 - 0.29mm and processing time of 10 – 13 frames per second. Similarly, current system achieved the overlay error from 0.23 - 0.35mm and processing time of 8 – 12 frames per second. Conclusion: This research should reduce the computation time of the TLD algorithm and improve the accuracy of it.