A tooth x-ray image matching method

Abstract

The invention relates to a tooth X-ray image matching method based on SURF point matching and RANSAC model estimation. The tooth X-ray image matching method includes the steps that (1), images are collected; (2), the images are enhanced; (3), features are extracted; (4), the features are matched; (5), related matching coefficients are calculated; (6), a matching result is displayed; (7), if reference images which do not participate in matching exist in an image library, the step (1) is carried out, a new reference image is selected from the image library, and if all images participate in matching, operation is finished; (8), matching succeeds, personal information corresponding to the reference images is recorded, and then operation is finished. The feature points of an input tooth image and a reference tooth image are extracted according to an SUFR algorithm, then the feature points are matched according to an RANSAC algorithm, and finally, the matching degree of the two images is measured according to the correlation coefficient of the two matched images. Experiment shows that by the tooth X-ray image matching method, the high precision ratio and high real-time performance are achieved.

Description

technical field [0001] The invention relates to a tooth X-ray image matching method, which belongs to the technical field of criminal investigation information. Background technique [0002] The identification of unknown corpses is a key issue in the judicial field. With the continuous emergence of vicious criminal cases and catastrophic accidents such as explosions, air crashes, tsunamis, fires, and car accidents, many identification methods based on organic substances, such as lip prints, fingerprints, and irises, often cannot play an ideal role in identification. , or even completely lose value. For such unidentified unknown bones, the shape of the teeth will become a unique identity feature. Teeth are the hardest tissue in the human body, with strong heat resistance and corrosion resistance. For different individuals, the probability of identical dental features is only one in 2.5 billion, so it is called another "identity card" by forensic dentists. In view of this ...

AI Technical Summary

Problems solved by technology

[0018] But the above algorithms all have flaws: First, the tooth segmentation will destroy the characteristics of the teeth

Secondly, all the literature uses the edge of the tooth as a feature, but the edge may not be the most effective feature, so the process of feature extraction lacks adaptability

Thirdly, medical images are often images with poor quality, high noise, uneven illumination, and blurred edges. It is difficult to achieve ideal results in image segmentation and edge extraction, which makes the system less flexible.

Finally, many literatures use the bitewing image as the input image, but the shooting of the bitewing image needs to be taken by the photographer biting the cardboard wing, which is obviously not feasible for the unknown skeleton in practical applications

Images