An effective dental work extraction and matching method for bitewing radiographs

This paper presents a method of dental work (DW) extraction and matching for bitewing radiographs. The method includes an algorithm that can correctly extract DW´s from radiograph images and two matching metrics (d_FD of frequency domain and d_XOR of spatial domain) that can effectively match a postmortem DW to the genuine antemortem DW in the database. The experimental results show that our method can extract DW´s more correctly shape- and number-wise than methods that use global thresholding. The results also show that, for a database containing 52 different shaped DW´s, the accuracy based on d_FD is 95% when using top 6% retrievals and achieves to 100% when using top 17% retrievals; whereas the accuracy based on d_XOR is 86 and 95 %, respectively, when using the same percentage retrievals. For a database containing 10% of hoax DW´s (i.e., DW´s have the same shape but different orientation/position as some genuine DW´s), the accuracy based on both metrics maintains about the same except the top-1 match based on d_FD. The fact that d_XOR was not affected by hoax DW´s indicates that d_FD and d_XOR can compensate each other when matching the postmortem DW with hoax DW´s. Comparing with the 95% and 100% hit rates using top 8% and 47% retrievals from a much bigger database reported in literature, the metric d_FD not only is more efficient but gives a better result.