牙齒特徵是電腦輔助診斷很重要的要素，牙齒分割是提取牙齒特徵很重要的一個步驟，正確的把牙齒分割能有效的提高牙齒特徵明確度。在現今牙齒分割中常以灰階投影的總和值來判斷牙縫以及咬合面的正確位置，然而X光片上牙齒的傾斜導致牙縫角度的不一致以及牙冠間過於密合導致從單一角度的灰階值投影無法以單純的極小值與角度去定位牙縫切割線位置，所以我們在此介紹另一個以Canny edge為主的牙齒切割。為了能符合更多的X光的牙縫，我們不在利用單一閾值和假定牙齒寬度，這邊利用了Canny edge和Hough line transform 來找到符合牙縫的線段，並以線段區域狀況對全部的線段作分群，以此畫出有可能的分割牙齒線，最後根據每張圖的線段間距與線段灰階值來刪除錯誤的分割線來達成最後目的，在我們的資料共416顆牙齒中，我們抓到了354顆牙齒，正確率為85.09%。

Dental features are an important element of computer-aided diagnosis. Teeth segmentation is a very important step in extracting tooth features. Correctly segmenting the teeth can effectively improve the clarity of the teeth. In the tooth segmentation, the integral projection is often used to determine the correct position of the teeth and the occlusal surface. However, the inclination of the teeth on the X-ray film leads to the inconsistency of the angle of the teeth and the excessive tightness between the crowns, so that the integral projection of the gray-scale value from a single angle cannot locate the position of the dental cutting line with a minimum value and angle. So we introduce another teeth segmentation based on Canny edge. In order to fit slit between the teeth, we are not using a single threshold and assumed tooth width. We use Canny edge and Hough line transform to find the line segments that match the teeth, and group all the line segments by its local condition. This draws a possible segmentation of the tooth line. This draws a possible segmentation of the tooth line. Finally, the wrong segmentation line is deleted according to the width of segmentation lines and the segmentation line integral projection to achieve the final goal. In our data, we have 416 teeth and then we detect 354 teeth. Correct rate obtains 85.09%

[1] S. Datta and N. Chaki, "Detection of dental caries lesion at early stage based on image analysis technique," in 2015 IEEE International Conference on Computer Graphics, Vision and Information Security (CGVIS), 2015: IEEE, pp. 89-93.
[2] A. Bhan, A. Goyal, N. Chauhan, and C.-W. Wang, "Feature line profile based automatic detection of dental caries in bitewing radiography," in 2016 International Conference on Micro-Electronics and Telecommunication Engineering (ICMETE), 2016: IEEE, pp. 635-640.
[3] J. Choi, H. Eun, and C. Kim, "Boosting proximal dental caries detection via combination of variational methods and convolutional neural network," Journal of Signal Processing Systems, vol. 90, no. 1, pp. 87-97, 2018.
[4] P. Lin, Y. Lai, and P. Huang, "An effective classification and numbering system for dental bitewing radiographs using teeth region and contour information," Pattern Recognition, vol. 43, no. 4, pp. 1380-1392, 2010.
[5] P.-L. Lin, Y.-H. Lai, and P.-W. Huang, "Dental biometrics: Human identification based on teeth and dental works in bitewing radiographs," Pattern Recognition, vol. 45, no. 3, pp. 934-946, 2012.
[6] O. Nomir and M. Abdel-Mottaleb, "A system for human identification from X-ray dental radiographs," Pattern Recognition, vol. 38, no. 8, pp. 1295-1305, 2005.
[7] C.-W. Wang et al., "A benchmark for comparison of dental radiography analysis algorithms," Medical image analysis, vol. 31, pp. 63-76, 2016.
[8] T. Acharya and A. K. Ray, Image processing: principles and applications. John Wiley & Sons, 2005.
[9] P.-L. Lin, P.-W. Huang, Y. Cho, and C.-H. Kuo, "An automatic and effective tooth isolation method for dental radiographs," Opto-Electronics Review, vol. 21, no. 1, pp. 126-136, 2013.
[10] P. Pandey, A. Bhan, M. K. Dutta, and C. M. Travieso, "Automatic image processing based dental image analysis using automatic Gaussian fitting energy and level sets," in 2017 International Conference and Workshop on Bioinspired Intelligence (IWOBI), 2017: IEEE, pp. 1-5.
[11] J. Naam, J. Harlan, S. Madenda, and E. P. Wibowo, "The algorithm of image edge detection on panoramic dental X-Ray using multiple morphological gradient (MMG) method," International Journal on Advanced Science, Engineering and Information Technology, vol. 6, no. 6, pp. 1012-1018, 2016.
[12] J. Naam, "Accuracy of Panoramic Dental X-Ray Imaging in Detection of Proximal Caries with Multiple Morpological Gradient (mMG) Method," JOIV: International Journal on Informatics Visualization, vol. 1, no. 1, pp. 5-11, 2017.
[13] A. K. Jain and H. Chen, "Matching of dental X-ray images for human identification," Pattern recognition, vol. 37, no. 7, pp. 1519-1532, 2004.
[14] L. A. Piegl, "B(asic)−spline basics," in Fundamental developments of computer-aided geometric modeling: Academic press, 1993, pp. 27-49.