Method for tooth surface classification
View Patent ↗A method for intraoral imaging obtains a digital image of one or more teeth and detects first and second boundaries. At each of the first and second boundaries, there is calculated a boundary ratio of mean gray-scale values for the tooth area on one side of the boundary to mean gray-scale values for background areas on the other side. The calculated boundary ratios are stored. A third ratio of the mean gray-scale values for the tooth area near the first boundary to the mean gray-scale values for the tooth area near the second boundary is calculated and stored. A vector is formed and stored that contains at least the calculated boundary ratios and the third ratio. The tooth surface is classified as either smooth or occlusal according to the stored vector. The image data is processed according to the classification and processing results are reported.
1. A method for intraoral imaging, the method executed at least in part on a computer system and comprising:
obtaining a digital image of one or more teeth;
detecting first and second boundaries of the one or more teeth;
calculating, at each of the first and second boundaries, a boundary ratio of mean gray-scale values for the tooth area on one side of the boundary to mean gray-scale values for background areas on the other side of the boundary and storing the calculated boundary ratios in a memory;
calculating a third ratio of the mean gray-scale values for the tooth area near the first boundary to the mean gray-scale values for the tooth area near the second boundary and storing the third ratio in the memory;
forming and storing a vector that contains at least the calculated boundary ratios and the third ratio;
classifying a tooth surface as either smooth or occlusal according to the stored vector;
processing the digital image according to the tooth surface classification; and
reporting the processing results.
2. The method of claim 1 wherein the mean gray scale values are from portions of the image that are within one third of the distance between the first and second boundaries.
3. The method of claim 1 wherein classifying the tooth surface comprises using a principal component analysis classifier.
4. The method of claim 1 wherein classifying the tooth surface comprises using a trained classifier.
5. The method of claim 1 wherein processing the digital image according to the tooth surface classification comprises detecting one or more caries sites.
6. The method of claim 5 wherein reporting the processing results comprises highlighting the one or more caries site on a display.
7. The method of claim 1 wherein the stored vector is normalized according to values from a training data set.
8. The method of claim 1 wherein the boundaries include one or more of gum areas and background areas.
9. A method for caries detection, the method executed at least in part on a computer system that has a display and comprising:
obtaining a digital image of one or more teeth;
detecting first and second boundaries of the one or more teeth;
calculating, at each of the first and second boundaries, a boundary ratio of mean gray-scale values for the tooth area on one side of the boundary to mean gray-scale values for background areas on the other side of the boundary and storing the calculated boundary ratios in a memory;
calculating a third ratio of the mean gray-scale values for the tooth area near the first boundary to the mean gray-scale values for the tooth area near the second boundary and storing the third ratio in the memory;
forming and storing a vector that contains at least the calculated boundary ratios and the third ratio;
classifying a tooth surface as either smooth or occlusal according to the stored vector;
processing the digital image to detect caries according to the tooth surface classification; and
reporting the processing results on a display.
10. The method of claim 9 wherein reporting the processing results comprises highlighting one or more caries site on the display.