Method for locating an interproximal tooth region
A method for locating one or more interproximal tooth regions in a digital tooth image. The method can be executed at least in part on data processing hardware. The method includes generating the digital tooth image from a fluorescence image of one or more teeth and a reflectance image of the one or more teeth, so as to combine image data from the fluorescence and reflectance images. The digital tooth image has intensity values for pixels corresponding to the one or more teeth and background. The method identifies one or more tooth regions by processing the digital tooth image and locates the one or more interproximal tooth regions according to the one or more identified tooth regions.
1. A method for locating one or more interproximal tooth regions in a digital tooth image executed at least in part by a processor, comprising:
accessing a fluorescence image of one or more teeth;
accessing a reflectance image of the one or more teeth;
generating the digital tooth image from the fluorescence and reflectance images, the digital tooth image comprising intensity values for pixels corresponding to a background and the one or more teeth;
automatically identifying one or more tooth regions by processing the pixels in the digital tooth image; and
automatically locating the one or more interproximal tooth regions according to the one or more identified tooth regions;
wherein locating the one or more interproximal tooth regions comprises;
determining internal markers in the tooth regions and external markers in the background according to a binary image of the digital tooth image;
applying a marker-controlled watershed transformation to a gradient image of a grayscale version of the digital tooth image with the internal and external markers to form two groups of water basins; and
identifying at least a first interproximal tooth region as those pixels having substantially the same distance to the first and second groups of water basins.
2. The method of claim 1 further comprising determining whether adjacent teeth in the one or more identified tooth regions are separated.
3. The method of claim 1 , wherein locating the one or more interproximal tooth regions comprises:
applying a distance transformation to a binary image of the digital tooth image to locate a first pixel wherein the first pixel lies within a first tooth region and wherein the first pixel has a largest distance from the boundaries of the first tooth region;
assigning the first tooth region that is connected to the located first pixel as a first object;
assigning a second tooth region that is not connected to the located first pixel as a second object; and
identifying a first interproximal region to be the pixels in the background having substantially the same distance to the first and second objects.
4. The method of claim 1 , wherein locating the one or more interproximal tooth regions comprises:
defining an origin point in a target tooth in a binary image of the digital tooth image;
casting a fan of ray lines outward from the origin point in the target tooth in a plurality of angles;
defining a contour line at points at which each ray line first encounters a boundary between tooth and background areas,
determining internal markers in the tooth regions and external markers in the background from within the binary image;
applying a marker-controlled watershed transformation to a gradient image of a grayscale version of the digital tooth image with the internal and external markers to form first and second groups of water basins; and
identifying at least a first interproximal tooth region as those pixels having substantially the same distance to the first and second groups of water basins.
5. The method of claim 1 , wherein locating the one or more interproximal tooth regions comprises:
determining markers for a targeted tooth, one or more neighboring teeth, and background from the digital tooth image;
applying a marker-controlled watershed transformation to a gradient image of a grayscale version of the digital tooth image with the markers to form two groups of water basins; and
identifying at least a first interproximal tooth region as those pixels having substantially the same distance to the two groups of water basins.
6. The method of claim 1 further comprising displaying at least a first interproximal region.
7. The method of claim 1 further comprising:
storing in a memory, transmitting using the processor, or displaying using a display, the located one or more interproximal tooth regions.
8. A method for locating one or more interproximal regions in a digital tooth image executed at least in part by a processor wherein adjacent teeth have no clear demarcation, comprising:
defining an origin point in a target tooth in a binary image of the digital tooth image;
casting a fan of ray lines outward from the origin point in the target tooth in a plurality of angles in the digital tooth image;
defining a contour line at points at which each ray line first encounters a boundary between tooth and background areas in the digital tooth image;
determining internal markers in the tooth areas and external markers in the background areas from the binary image of the digital tooth image;
applying a marker-controlled watershed transformation to a gradient image of a grayscale version of the digital tooth image with the internal and external markers to form first and second groups of water basins; and
automatically identifying at least a first interproximal region in the digital tooth image as those pixels having substantially the same distance to the first and second groups of water basins by said processor.
9. The method of claim 8 wherein the digital tooth image is a fluorescence image.
10. The method of claim 8 wherein the digital tooth image is obtained by combining image data for fluorescence and reflectance images of the tooth.
11. The method claim 8 further comprising:
storing, transmitting, or displaying the identified at least first interproximal region in the digital tooth image.
12. A method for locating one or more interproximal regions in a 2D digital tooth image executed at least in part by a processor, comprising:
applying a distance transformation to a binary image of the digital tooth image, to form a distance image, the binary image of the 2D digital tooth image including background regions and one or more tooth regions, where a pixel value in the distance image represents a distance of that pixel to the background regions;
determining internal and external markers in the 2D digital tooth image using the distance image;
applying a marker-controlled watershed transformation to a gradient image of a grayscale version of the 2D digital tooth image combined with the internal and external markers to form two groups of water basins; and
automatically identifying at least a first interproximal region in the 2D digital tooth image as those pixels having substantially the same distance to the two groups of water basins by said processor.
13. The method of claim 12 wherein the digital tooth image is a fluorescence image.
14. The method of claim 12 wherein the digital tooth image is obtained by combining image data for fluorescence and reflectance images of the tooth.
15. The method claim 12 further comprising:
storing, transmitting, or displaying the identified at least first interproximal region in the digital tooth image.