ARI-ORB: Adaptive Rotation-Invariant ORB for Enhanced Feature Matching in Dental X-Ray Imaging

Feature matching occupies a significant place in computer vision and some algorithms for speed and accuracy with an equal ratio includes ORB, SIFT, and AKAZE. In this paper, we propose a new modified ORB feature matching approach named ARI-ORB, incorporating the Rotation- Invariant capability for generating a more adaptive. Recent developments have pointed out a need for permutation invariant deep learning models that can be applied on Dental Panoramic X-Ray images. Thus, ARI-ORB coping with problems studied from noisy and rotationally varied datasets employs the three sub-modules: descriptor aggregation, rotation invariance, and adaptive key-point selection. Experimental analysis of the proposed ARI-ORB approach on separate dental X-ray datasets yields 82.55% precision, 83.13% accuracy, 82.55% recall, 82.55% F1 score, and a PDR of 41.28%. Compared to baseline algorithms, ARI-ORB significantly outperforms ORB (F1: 58.40, PDR: 29.20), SIFT with (F1 value: 46.71, PDR: 23.35), AKAZE with (F1 value of: 53.74 PDR: 26.87), BRISK with (F1 value: 36.03, PDR: 18.01), FAST (F1: 17.42 PDR: 8.71). Moreover, the average execution time was 0.1548 seconds per image, indicating good computational performance. Described visualizations of feature matches and match distance distributions show that the method is viable, especially in adverse imaging conditions.