臺灣博碩士論文加值系統

自動化牙齒身份辨識系統(Automated Dental Identification System, ADIS)在法證界中是一個相當重要的身份辨識技術，主要目的是用來確認身體組織遭受到嚴重破壞的罹難者或是失蹤人口的身份。在本篇論文中，我們提出了一套基於牙齒X光咬翼片之自動化牙齒身份辨識系統，其中包含:牙齒X光片影像增強(enhancement)、影像切割(segmentation)、牙齒分類(classification)、牙齒編號(numbering)、以及牙齒辨識(identification)等功能。
在影像增強階段，我們結合同態濾波(homomorphic filtering)、自適性對比延展(adaptive contrast stretching)以及自適性形態學轉換(adaptive morphological transformation)等方法來同時增強牙齒X光片的對比度以及改善曝光不一致的問題。在影像切割階段，我們提出結合疊代門檻值法(iterative thresholding)以及疊代積分投影(iterative integral projection)法來進行牙齒與牙髓的切割與分隔。並且利用一個兩階段式的牙齒治療(dental work)切割法來進行補牙(filling)之萃取。在牙齒分類階段，我們提出一個牙齒歪斜糾正(skew-adjusted)的方法來有效取得正確的牙齒與牙髓相對長寬比(length/width ratio)，以及搭配相對的牙齒大小作為特徵值進行牙齒分類。在牙齒編號階段，我們結合一個缺牙偵測(missing teeth detection)演算法和一個序列比對(sequence alignment)方式來給予每顆牙齒一個特定的編號。最後，我們利用牙齒以及補牙之形狀作為比對之依據，進行牙齒身份辨識。為了減少不適用(unreliable contour)和不完整(incomplete contour)之邊界所造成的對位錯誤(alignment error)，我們提出一個有效邊界之距離權重(effective contour alignment based on weighted Hausdorff distance)對位法來提升比對之準確率。同時，為了彌補在空間域中對位不完全(imperfect alignment)的問題，我們利用具有對位不變性(alignment-invariant)的頻率域特徵作為互補。實驗結果證實我們所提出之方法確實能夠有效的提升分類、編號、以及辨識之準確率。

Automated dental identification system (ADIS) is an important human identification system designed for law enforcement to identify victims or missing people who are under severe decaying of soft tissues of the body. In this dissertation, we establish an ADIS to effectively enhance, segment, classify, number, and identify the teeth in dental bitewing radiographs.
An image enhancement method that combines enhanced homomorphic filtering, homogeneity-based contrast stretching, and adaptive morphological transformation is proposed to improve both contrast and illumination evenness of the radiographs simultaneously. Iterative thresholding and iterative integral projection are adapted to isolate teeth to regions of interest (ROIs) followed by contour extraction of the tooth and the pulp from each ROI. A dental works (DW) segmentation method based on the two-stage algorithm is adopted to extract the contours of DWs. A binary linear support vector machine using the skew-adjusted relative length/width ratios of both teeth and pulps, and crown size as features is proposed to classify each tooth to molar or premolar. A numbering scheme that combines a missing teeth detection algorithm and a simplified version of sequence alignment commonly used in bioinformatics is presented to assign each tooth a proper number. Finally, an enhanced dental identification method based on both the contours of teeth and dental works is presented. For reducing the alignment error caused from unreliable contours, a point-reliability measuring method is proposed when calculating Hausdorff distance between the contours. For reducing the alignment error caused from incomplete tooth contours, an outlier detection method is proposed to prune the outlier from each contour and realign the pruned contours. And for compensating the error when matching with the spatial feature of DWs due to imperfect alignment of the teeth in which they reside, an additional alignment-invariant frequency feature of DWs is used.
Experimental results show that our proposed system can achieve (1) 95.1% and 98% for classification and numbering, respectively, in terms of number of teeth tested, and correctly classifies and numbers the teeth in four image that were reported either misclassified or erroneously numbered, respectively; (2) 94.3% and 100% image retrieval accuracy of the top-1 and -5 retrievals, respectively, when matching with weighted HD of the pruned contour of a single tooth, which is superior to a method that matched with the traditional HD of two or three adjacent teeth; (3) 100% accuracy of top-2 (top 6%) image retrievals when matching with both contours of teeth and dental works, which again is superior to a method that matched with the size of non-registered tooth contours and non-overlapped dental works of a pair of teeth.

Chapter 1. Introduction...1
1.1. Problem Domain Descriptions...1
1.2. Goal of the Research...2
1.3. Major Contributions...4
1.4. Organization of the Dissertation...6

Chapter 2. Dental Biometrics and ADIS...8
2.1. Biometric Recognition...8
2.2. Automated Dental Identification System (ADIS)...8
2.2.1. The framework of ADIS...10
2.2.2. The functionality of ADIS...11
2.2.3. Performance measure of biometric systems...11

Chapter 3. Dental Radiograph Enhancement...13
3.1. Overview of Dental Image Enhancement...14
3.2. A Method for Dental Image Enhancement...16
3.2.1. Enhanced homomorphic filtering...17
3.2.2. Adaptive contrast stretching based on homogeneity...19
3.2.3. Adaptive morphological transformation...23
3.3. Dental Image Enhancement Algorithm...24
3.4. Experimental Results and Discussion...27
3.4.1. Enhancement results...27
3.4.2. Unsolved or failure cases...28

Chapter 4. Dental Radiograph Segmentation...33
4.1. Teeth Segmentation...34
4.2. Teeth Isolation...36
4.2.1. Separation between the upper and lower jaws...36
4.2.2. Isolation of each individual tooth...38
4.2.3. Iterative teeth isolation...39
4.3. Pulp Extraction...42
4.4. Dental Works Extraction...43
4.5. Experimental Results and Discussion...44
4.6.1. Performance of teeth isolation...44
4.6.2. Performance of teeth and pulp extraction...47
4.6.3. Performance of dental works extraction...48

Chapter 5. Teeth Classification and Numbering...52
5.1. Overview of Teeth Classification and Numbering...54
5.1.1. Teeth classification...54
5.1.2. Teeth numbering...55
5.2. A Teeth Classification Method...56
5.2.1. ROI extension with angle adjustment...56
5.2.2. ROI feature extraction...58
5.2.3. Support vector machine...60
5.3. A Teeth Numbering Method...61
5.3.1. Teeth standard patterns...62
5.3.2. Teeth sequence formation...63
5.3.3. Teeth alignment and numbering algorithm...65
5.3.4. Numbering examples of teeth numbering...68
5.4. Experimental Results and Comparisons...69
5.4.1. Experimental result of teeth classification...69
5.4.2. Experimental result of teeth numbering...70
5.4.3. Comparisons...72
5.4.4. Unsolved or failure cases...74

Chapter 6. Dental Radiograph Identification...76
6.1. Overview of Dental Image Identification...78
6.2. Tooth Contour Extraction and Representation...80
6.2.1. Contour alignment based on weighted Hausdorff distance...82
6.2.2. Effective contour alignment based on weighted Hausdorff distance...88
6.3. Dental Work Contour Extraction and Representation...91
6.4. Dental Identification...95
6.4.1. Metric for teeth matching...95
6.4.2. Metric for dental work matching...96
6.4.3. Metric for image matching...99
6.5. Experimental Results and Comparisons...100
6.5.1. Performance of teeth matching...102
6.5.2. Performance of dental works matching...104
6.5.3. Performance of image matching...104
6.5.4. Comparisons...107
6.5.5. Discussion...108

Chapter 7. Conclusions and Future Works...110
7.1. The Key Results...110
7.2. Suggestions for Future Works...113

Bibliography...116

[1]A. K. Jain, A. Ross, and S. Prabhakar, "An Introduction to Biometric Recognition," IEEE Transactions on Circuits and Systems for Video Technology, Vol. 14, pp. 4-20, 2004.
[2]X. Zhang and Y. Gao, "Face Recognition Across Pose: A Survey," Pattern Recognition, Vol. 42, pp. 2876-2896, 2009.
[3]K. W. Bowyer, K. Hollingsworth, and P. J. Flynn, "Image Understanding for Iris Biometrics: A Survey," Computer Vision and Image Understanding, Vol. 220, pp. 281-307, 2008.
[4]G. Fahmy, D. Nassar, E. Haj-Said, H. Chen, O. Nomir, J. Zhou, R. Howell, H. H. Ammar, M. Abdel-Mottaleb, and A. K. Jain, "Toward an Automated Dental Identification System (ADIS)," Journal of Electronic Imaging, Vol. 14, pp. 1-13, 2005.
[5]P. L. Lin, Y. H. Lai, and P. W. Huang, "An Effective Classification and Numbering System for Dental Bitewing Radiographs Using Teeth Region and Contour Information," Pattern Recognition, Vol. 43, pp. 1380-1392.
[6]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.
[7]I. A. Pretty and D. Sweet, "A Look at Forensic Dentistry- Part 1: The Role of Teeth in the Determination of Human Identity," British Dental Journal, Vol. 190, pp. 359-366, 2001.
[8]United States Army Institute of Dental Research Walter Reed Army Medical Center, "Computer Assisted Post Mortem Identification via Dental and Other Characteristics," USAIDR Information Bulletin, Vol. 5, 1990.
[9]B. G. Brogdon, Forensic Radiology, CRC Press, Boca Raton, 1998.
[10]P. Stimson and C. Mertz, Forensic Dentistry, CRC Press, Boca Raton, 1997.
[11]Gustafson and Ghosta, Forensic Odontology, American Elsevier Pub. Co., 1996.
[12]O. Nomir and M. Abdel-Mottaleb, "A System for Human Identification from X-ray Dental Radiographs," Pattern Recognition, Vol. 38, pp. 1295-1305, 2005.
[13]O. Nomir and M. Abdel-Mottaleb, "Fusion of Matching Algorithms for Human Identification using Dental X-ray Radiographs," IEEE Transactions on Information Forensics and Security, Vol. 3, pp. 223-233, 2008.
[14]M. Abdel-Mottaleb, O. Nomir, D. E. Nassar, G. Fahmy, and H. H. Ammar, "Challenges of Developing an Automated Dental Identification System," Proceeding of the IEEE Mid-west Symposium for Circuits and Systems, Vol. 1, pp. 411-414, 2003.
[15]P. L. Lin, Y. H. Lai, and P. W. Huang, "Dental Biometric: Human Identificaiton Based on Teeth and Dental Works in Bitewing Radiographs," revised for Pattern Recognition.
[16]O. Nomir and M. Abdel-Mottaleb, "Human Identification from Dental X-ray Images based on the Shape and Appearance of the Teeth," IEEE Transactions on Information Forensics and Security, Vol. 2, pp. 188-197, 2007.
[17]P. L. Lin and Y. H. Lai, "An Effective Classification System for Dental Bitewing Radiographs using Entire Tooth," Proceedings of the 2009 WRI Global Congress on Intelligent Systems (GCIS 2009), pp. 369-373, 2009.
[18]P. L. Lin and Y. H. Lai, "An Effective Teeth Positioning System for Dental Bitewing Radiographs Based on Classification Results," International Forum on Medical Imaging in Asia 2009, pp. 633-638, 2009.
[19]P. H. Lin, Y. H. Lai, and C. H. Kuo, "Dental Identification Based on Teeth and Dental Works Matching for Bitewing Radiograph," International Forum on Medical Imaging in Asia 2011, pp. 149-155, 2011.
[20]National Biometric Security Project (NBSP), Biometric Technology Application Manual, 2008.
[21]J. L. Wayman, "Fundamentals of Biometric Authentication Technologies," International Journal of Image and Graphics, Vol. 1, pp. 93-113, 2001.
[22]American Society of Forensic Odontology, "Forensic Odontology News," Vol. 16, 1997.
[23]United States Army Institute of Dental Research Walter Reed Army Medical Center, "Computer Assisted Post Mortem Identification via Dental and other Characteristics," USAIDR Information Bulletin, Vol. 5, 1990.
[24]J. McGivney et al. WinID2 software. (http://www.windid.com).
[25]E. H. Said, D. E. M. Nassar, G. Fahmy, and H. H. Ammar, "Teeth Segmentation in Digitized Dental X-ray Films Using Mathematical Morphology," IEEE Transactions on Information Forensics and Security, Vol. 1, pp. 178-189, 2006.
[26]E. Whaites, Essentials of Dental Radiography and Radiology, second edition, Churchill Livingstone, 1996.
[27]R. C. Gonzalez and R. E. Woods, Digital Image Processing, second edition, Prentice Hall, 2002.
[28]E. Said, G. Fahmy, D. Nassar, and H. Ammar, "Dental X-ray Image Segmentation," Proceeding of the SPIE, the Biometric Technology for Human Identification conference, Vol. 5404, pp. 409-417, 2004.
[29]M. H. Mahoor and M. Abdel-Mottaleb, "Classification and Numbering of Teeth in Dental Bitewing Images," Pattern Recognition, Vol. 38, pp. 577-586, 2005.
[30]Y. H. Lai and P. L. Lin, "Effective Segmentation for Dental X-ray Images using Texture-based Fuzzy Inference System," Advanced Concepts for Intelligent Vision System, LNCS 5259, pp. 936-947, 2008.
[31]T. Acharya and A. K. Ray, Image Processing: Principles and Applications, Wiley-Interscience, 2005.
[32]L. G. Shapiro and G. C. Stockman, Computer Vision, Prentice Hall, 2001.
[33]R. C. Gonzalez and P. Wintz, Digital Image Processing, Addison-Wesley Publishing Company, Reading, MA, 198.
[34]H. D. Cheng, M. Xue, X. J. Shi, "Contrast Enhancement based on a Novel Homogeneity Measurement," Pattern Recognition, Vol. 36, pp. 2687-2697, 2003.
[35]T. D. Sterling, S. V. Pollack, Introduction to Statistical Data Processing, Prentice-Hall, Englewood Cli2s, NJ, 1968.
[36]W. L. Quirin, Probability and Statistics, Harper & Row, New York, 1978.
[37]R. S. King and B. Julstrom, Applied Statistics Using the Computer, Alfred Publishing Co., Sherman Oaks, CA, 1982.
[38]A. Moragas, M. Garcia-Bonafe, I. de Torres, and M. Sans, "Textural Analysis of Lymphoid Cells in Serous Effusions. A mathematical Morphologic Approach," Analytical and Quantitative Cytology and Histology, Vol. 15, pp. 165-170, 1993.
[39]C. Giardina and E. Doughetr, Morphological Methods in Image and Signal Processing, Prentice-Hall, Englewood Cliffs, NJ, 1988.
[40]D. L. Pham, C. Xu, and J. L. Prince, "A Survey of Current Methods in Medical Image Segmentation," In Annual Review of Biomedical Engineering, Vol. 2, pp. 315-338, 2000.
[41]H. Zhang, J. E. Fritts, and S. A. Goldman, "Image Segmentation Evaluation: A Survey of Unsupervised Methods," Computer Vision and Image Understanding, Vol. 110, pp. 260-280, 2008.
[42]A. K. Jain and H. Chen, "Matching of Dental X-ray Images for Human Identification," Pattern Recognition, Vol. 37, pp. 1519-1532, 2004.
[43]F. Keshtkar and W. Gueaieb, "Segmentation of Dental Radiographs Using a Swarm Intelligent Approach," IEEE Canadian Conference on Electrical and Computer Engineering, pp. 26-33, 2006.
[44]H. Chen and A. K. Jain, "Dental Biometrics: Alignment and Matching of Dental Radiographs," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 27, pp. 1319-1326, 2005.
[45]M. Hofer and A. N. Marana, "Dental Biometrics: Human Identification based on Dental Work Information," XX Brazilian Symposium on Computer Graphics and Image Processing, pp. 281-286, 2007.
[46]S. Hu, E. A. Huffman, and M. Reinhardt, "Automatic Lung Segmentation for Accurate Quantization of Volumetric X-ray CT Images," IEEE Transactions on Medical Imaging, Vol. 20, pp. 490-498, 2001.
[47]J. F. Canny, "A Computational Approach to Edge Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, pp. 679-698, 1986.
[48]C. de Boor, "B-Spline Basics, Fundamental Developments of Computer-Aided Geometric Modeling," Academic Press, New York, pp. 27-49, 1993.
[49]C. H. Kuo and P. L. Lin, "An Effective Dental Work Extraction and Matching Method for Bitewing Radiographs," 2010 International Computer Symposium, pp. 495-499, 2010.
[50]J. Fan, G. Zeng, M. Bodey, and M. Hacid, "Seeded Region Growing: An Extensive and Comparative Study," Pattern Recognition Letter, Vol. 26, pp. 1139-1156, 2004.
[51]American Dental Association, Current Dental Terminology, third edition (CDT-3), 1999.
[52]S. Tabbone, L. Wendling, and J. –P. Salmon, "A New Shape Descriptor Defined on the Radon Transform," Computer Vision and Image Understanding, Vol. 102, pp. 42-51, 2006.
[53]A. K. Jain and H. Chen, "Registration of Dental Atlas to Radiographs for Human Identification," Proceeding of SPIE Conference on Biometric Technology for Human Identification, Vol. 5779, pp. 292-298, 2005.
[54]C. Cortes and V. Vapnik, "Support-vector Network," Matching Learning, Vol. 20, pp. 273-297, 1995.
[55]J. C. Burges, "A Tutorial on Support Vector Machines for Pattern Recognition," Data Mining and Knowledge Discovery, Vol. 2, pp. 121-167, 1998.
[56]V. Vapnik, The Nature of Statistical Learning Theory, Springer, New York, NY, 1995.
[57]P. N. Tan, M. Steinbach, and V. Kumar, Introduction to Data Minining, Addison-Wesley, 2006.
[58]C. C. Chang and C. J. Lin, LIBSVM: A Library for Support Vector Machines, 2001, software available at (http://www.csie.ntu.edu.tw/~cjlin/libsvm).
[59]T. F. Smith and M. S. Waterman, "Identification of Common Molecular Subsequences," Journal of Molecular Subsequences, Vol. 147, pp. 195-197, 1981.
[60]O. Nomir and M. Abdel-Mottaleb, "Hierarchical Contour Matching for Dental X-ray Radiographs," Pattern Recognition, Vol. 41, pp. 130-138, 2008.
[61]D. P. Huttenlocher, G. A. Klanderman, and W. J. Rucklidge, "Comparing Images Using the Hausdorff Distance," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 15, pp. 850-863, 1993.
[62]C. Zhao, W. Shi, and Y. Deng, "A New Hausdorff Distance for Image Matching," Pattern Recognition Letter, Vol. 26, pp. 581-586, 2005.
[63]V. Chandola, A. Banerjee, and V. Kumar, "Outlier Detection: A Survey, Technical Report," University of Minnesota, 2007.