A novel visualization system of using augmented reality in knee replacement surgery: Enhanced bidirectional maximum correntropy algorithm

Background and Aim Image registration alignment are the main limitations of augmented reality (AR)-based knee replacement surgery. This research aims to decrease error, eliminate outcomes that trapped in local minima improve problems, handle occlusion maximize overlapping parts. Methodology Markerless image method was used for AR-based surgery guide visualize surgical operation. While weight least square algorithm enhance stereo camera-based tracking by filling border right-to-left direction non-border from left-to-right direction. Results study has improved video precision 0.57–0.61 mm error. Furthermore, with use bidirectional points, is, forward backward directional cloud point, iteration on decreased. led processing time as well. The frames 7.4–11.74 per second. Conclusions It seems clear this proposed system focused overcoming misalignment difficulty caused movement patient enhancing AR visualization during reliable favourable which helps eliminating error ascertaining optimal rigid transformation between two points removing outliers non-Gaussian noise. accurate navigation anatomy such femur, tibia, cartilage, blood vessels so forth.