Please use this identifier to cite or link to this item:
標題: 應用於牙齒X光影像之牙齒分隔研究
An Effective Teeth Isolation Method for Dental X-ray Images
作者: 卓于生
Cho, Yu-Sheng
關鍵字: 牙齒x光影像;牙齒分隔;缺牙偵測
出版社: 資訊科學與工程學系所
引用: [1] Phen-Lan Lin, Yan-Hao Lai, and Chun-Hung KuoLin, Phen-Lan (2011/1). “Dental Identification based on Teeth and Dental Works Matching for Bitewing Radiographs,” IEICE technical report. 日本:IEICE電子通信協會. [2] A.K. Jain, H. Chen, S. Minut, “Dental biometrics: human identification using dental radiographs,” in: Proceedings of the Fourth International Conference on AVBPA, Guildford, UK, 2003, pp. 429–437. [3] Schuller-Gotzburg P, Suchanek J (2007) “Forensic odontologists successfully identify tsunami victims in Phuket,” Thailand. Forensic Sci Int 171(2–3):204–207 [4] F.S. Malkowski, “Forensic dentistry, a study of personal identification,” Dent. Stud. 51 (1972) 42–44. [5] V.W.Weedn, “Postmortem identifications of remains,” Clin. Lab. Med. 18 (1998) 115–137. [6] R.B. Dorion, “Disasters big and small,” J. Can. Dent. Assoc. 56 (1990) 593–598. [7] Phen-Lan Lin, Yan-Hao Lai, Po-Whei Huang (2010/4). “An Effective Classification and Numbering System for Dental Bitewing Radiographs Using Teeth Region and Contour Information,” Pattern Recognition, Vol. 4 , No. 43 , p.p.80 -92 .[SCI] [8] Lin, Phen-Lan (2008/5). “Effective Segmentation for Dental X-Ray Images Using Texture-Based Fuzzy Inference System,” ACIVS, 2008, LNCS5259 (p.p.936-947). Springer-Verlag, Berlin: Springer-Verlag, Berlin. [9] Phen-Lan Lin, Yan-Hao Lai, “An Effective Teeth Positioning System for Dental Bitewing Radiographs Based on Classification Results, ” 2008. [10] A.K. Jain and H. Chen, “Matching of Dental X-ray Images for Human Identification,” Pattern Recognition, Vol. 37, pp. 1519-1532, 2004. [11] O. Nomir and M. Abdel-Mottaleb, “A System for Human Identification from X-ray Dental Radiographs,” Pattern Recognition, Vol. 38, pp. 1295-1305, 2005. [12] J. Zhou and M. Abdel-Mottaleb “A content-based system for human identification based on bitewing dental X-ray images,” Pattern Recognition, Vol. 38, pp. 2132-2142, 2005. [13] Kass, M., A. Witkin, D. Terzopoulos, “Snakes: Active contour models,” International Journal of Computer Vision, Vol. 1, pp. 321–331, 1987. [14] Kang, D. J ., J. Y. Kim, I. S. Kweon, “A stabilized snake constraint for tracking object boundries, ” ISIE 2001,Pusan, KOREA. [15] Schnable, J. A., S. R. Arridge, “Active Contour Model for shape description using multiscale differential invarians,” British Machine Vision [16] Shen, D. G., C. Davatizikos, “An adaptive-focus deformable model using statistical and geometric information,” IEEE Transactions on pattern analysis and machine intelligence, Vol. 22, NO. 8, August 2000 [17] C. deBoor, B(asic)-spline basics, in: L. Piegl (Ed.), Fundamental Developments of Computer-Aided Geometric Modeling, Academic Press, New York, 1993, pp. 27–49. [18] Chien-Chang Lin, “Detection and Segmentation of Teeth in Dental Digital Images, ” Taiwan, 2005. [19] M. Sonka, V. Hlavac, R. Boyle, Image Processing, Analysis, and Machine Vision, second ed., Thomson, 2001. [20] L. Vincent, “Morphological grayscale reconstruction in image analysis: application and efficient algorithms,” IEEE Trans. Image Process. 2 (2) (1993) 176–201.
牙齒分隔在牙齒電腦輔助診斷系統,以及牙齒生物特徵辨識系統中是一個很重要的前處理動作,牙齒分隔結果的準確性,會直接影響到牙齒特徵萃取的精度,進而影響到電腦輔助診斷的結果及身份辨識的結果。因此我們提出了一個牙齒x光影像的有效牙齒分隔方法。在第一步驟中利用horizontal integral projection的資訊來分隔上下顎。在第二步驟中,我們利用了vertical integral projection配合變動視窗法及interdental papilla的資訊來分隔各個獨立的牙齒。第三步驟則是利用vertical integral projection的一階微分資訊尋找缺牙的位置,並且使用了一個型態學運算子來做影像去雜訊,再使用此去雜訊後影像做上下過度咬合或左右相鄰重疊的偵測。而實驗結果也顯示,我們的方法比已發表於文獻中的方法,更能在原始影像中出現曝光不均、大面積補牙等情形時,提供相對較好的分隔結果。

Teeth isolation is a very important pre-processing step of computer-aided dental diagnosis system and dental biometric system. The accuracy of the teeth isolation will directly affect the accuracy of feature extraction and thereby affecting the results of computer-aided diagnosis and the results of identity recognition. Therefore, we propose an effective teeth isolation method for dental X-ray images. In the first step we use the horizontal integral projection information to separate the upper and lower jaws. In the second step, we use the vertical integral projection with the dynamic window method and interdental papilla information to separate the individual teeth. The third step is to use the first derivative information of the vertical integral projection to find the location of missing teeth, and detect teeth occlusion/overlapping segments from the donoised image by bottom-hat operations. The experimental results show that our method, when compared to previous methods, gives better teeth isolation results, especially for image of uneven exposure or with large areas of dental work.
Appears in Collections:資訊科學與工程學系所

Show full item record

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.