Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/19630
DC FieldValueLanguage
dc.contributor陳錦杏zh_TW
dc.contributorChin-Hsing Chenen_US
dc.contributor詹永寬zh_TW
dc.contributor吳憲珠zh_TW
dc.contributorY. K. Chanen_US
dc.contributorHsien-Chu Wuen_US
dc.contributor.advisor喻石生zh_TW
dc.contributor.advisorShyr-Shen Yuen_US
dc.contributor.author曾筱芸zh_TW
dc.contributor.authorTseng, Hsiao-Yunen_US
dc.contributor.other中興大學zh_TW
dc.date2010zh_TW
dc.date.accessioned2014-06-06T07:07:12Z-
dc.date.available2014-06-06T07:07:12Z-
dc.identifierU0005-2007200912152100zh_TW
dc.identifier.citation[1] C. N. E. Anagnostopoulos, I. E. Anagnostopoulos, V. Loumos, and E. Kayafas, “A License Plate-Recognition Algorithm for Intelligent Transportation System Applications,” IEEE Transactions on Intelligent Transportation Systems, Vol. 7, No. 3, pp.377-392, 2006. [2] S. Arivazhagan, S. Deivalakshmi, K. Kannan, B. N. Gajbhiye, C. Muralidhar, S. N. Lukose, and M. P. Subramanian, “Multi-resolution system for artifact removal and edge enhancement in computerized tomography images,” Pattern Recogn. Lett., Vol.28, pp.1769-1780, 2007. [3] H. Bai, J. Zhu, and C. Liu, “A Fast License Plate Extraction Method on Complex Background,” IEEE Proceedings of Intelligent Transportation Systems, Vol. 2 pp.985-987, 2003. [4] J. C. Bezdek, “Fuzzy Mathematics in Pattern Classification,” New York: Cornell University, 1973. [5] J. Canny, “A Computational Approach to Edge Detection,” IEEE Trans. Pattern Anal. Vol.8, pp.679-698, 1986. [6] K. R. Castleman, “Digital Image Processing,” Prentice Hall International, Inc., New Jersey, 1996. [7] N. D. Levine Chairman, J. O. Corliss, F. E. G. Cox, G. Deroux, J. Grain, B. M. Honigberg, G. F. Leedaile, A. R. Loeblich, III. J. Lom, D. Lynn, E. G. Merinfeld, F. C. Page, G. Poljansky, V. Sprague, J. Vavra, and F. G. Wallace, “A Newly Revised Classification of the Protozoa,” J. Eukaryot. Microbiol., Vol. 27 pp.37-58, 1980. [8] S. L. Chang, L. S. Chen, Y. C. Chung, and S. W. Chen, “Automatic License Plate Recognition,” IEEE Transactions on Intelligent Transportation Systems, Vol. 5, No. 1, pp.42-53, 2004. [9] T. S. Chen, H. C. Wu, and C. H. Lai, “Multi-target Car License Plate Detection from Complex Environment,” Proceedings of IEEE International Workshop on Nonlinear Signal and Image Processing, pp. 399-403, 2005. [10] E. Davies, Machine Vision: Theory, Algorithms and Practicalities, Academic Press, 1990. [11] O. Duda, P. E. Hart and D. G. Stork, “Pattern Classification,” 2nd Edition, Richard John Wiley & Sons, 2001. [12] R. C. Gonzalez and P. Wintz, “Digital Image Processing,” 3rd Ed., Addison-Wesley, 1992. [13] Rafael C. Gonzalez, Richard E. Woods, “Digital Image Processing,” 2nd edition, Prentice Hall, Inc., 2002. [14] R. C. Gonzalez, R. E. Woods, and S. L. Eddins, “Digital Image Processing using Matlab,” Prentice Hall Pub., 2004. [15] N. Guo, L. Zeng, and Q. Wu, “A Method Based on Multispectral Imaging Technique for White Blood Cell Segmentation,” Comput. Biol. Med., Vol.37, pp.70-76, 2006. [16] E. M. Haacke, M. Ayaz, A. Khan, E. S. Manova, B. Krishnamurthy, L. Gollapalli, C. Ciulla, I. Kim, F. Petersen, and W. Kirsch, “Establishing a baseline phase behavior in magnetic resonance imaging to determine normal vs. abnormal iron content in the brain,” J. Magn. Reson. Imaging, Vol. 26 pp.265-273, 2007. [17] J. W. Hsieh, S. H. Yu, and Y. S. Chen, “Morphology-based License Plate Detection from Complex Scenes,” roceedings of 16th International Conference on Pattern Recognition, Vol. 3, pp. 176-179, 2002. [18] K. Jiang, Q. -M. Liao, and Y. Xiong, “A Novel White Blood Cell Segmentation Scheme Based on Feature Space Clustering,” Soft Comput., Vol.10, pp.12-19, 2006. [19] J. Jones and L. Palemer, “An Evaluation of the Two Dimensional Gabor Filter Medel of the Two Dimensional Gabor Filter Medel of Simple Receptive Fields in Cat Striate Cortex,” Journal Neurophysiology, Vol. 58, pp.1233-1258, 1987. [20] S. J. Lord, W. Lei, P. Craft, J. N. Cawson, I. Morris, S. Walleser, A. Griffiths, S. Parker, and N. Houssami, “A systematic review of the effectiveness of magnetic resonance imaging (MRI) as an addition to mammography and ultrasound in screening young women at high risk of breast cancer,” Eur. J. Cancer 431905-1917, 2007. [21] J. B. MacQueen, “Some Methods for classification and Analysis of Multivariate Observations,” Proc. 5th Berkeley Symp. Math. Stati. Prob., University of California Press 1 pp.281-297, 1967. [22] K. Z. Mao, Peng Zhao, and Puay-Hoon Tan, “Supervised Learning-Based Cell Image Segmentation for P53 Immunohistochemistry,” IEEE Transactions on Biomedical Engineering, Vol. 53, No. 6, 2006. [23] E. K. Markell, D. T. John, W. A. Krotoski, “Medical Parasitology,” 8th edition, W.B. Saunders Company, 1999. [24] T. Naito, T. Tsukada, K. Uamada, K. Kozuka, and S. Yamamoto, “Robust License-Plate Recognition Method for Passing Vehicles Under Outside Environment,” IEEE Transactions on Vehicular Technology, Vol. 49, No. 6, pp.2309-2319, 2000. [25] Yasuo Nakagawa, Azriel Rosenfeld, “Some Experiments on Variable Thresholding,” Pattern Recognition, Vol. 11, No. 3, pp.191-204, 1979. [26] T. W. Nattkemper, H. Wersing, W. Schubert, and H. Ritter, “A Neural Network Architecture for Automatic Segmentation of Fluorescence Micrographs,” Neurocomputing, Vol.48, pp.357-367, 2002. [27] T. V. Nguyen, V. P. Le, C. L. Huy, K. N. Gia, and A. Weintraub, “Detection and characterization of diarrheagenic Escherichia coli from young children in Hanoi, Vietnam,” J. Clin. Microbiol, Vol. 43, No. 2 pp.755-760, 2005. [28] Nobuyuki Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Transactions on Systems. Man, and Cybernet Ics, Vol. Smc 9, NO.1, 1979. [29] E. Pietka, S. Popiech, A. Gertych, F. Cao, H. K. Huang, and V. Gilsanz, “Computer Automated Approach to the Extraction of Epiphyseal Regions in Hand Radiographs,” J. Digit. Imaging, Vol.14, pp.165-172, 2001. [30] N. P. Sherwood and L. Heathman, “Further Studies on the Antigenic Properties of Pathogenic and Free Living Amebas. II. Complement Fixation in Amebic Dysentery,” Am. J. Epidemiol., Vol.16, pp.124-136, 1932. [31] B. R Thapa, K. Ventkateswarlu, A. K. Malik and D. Panigrahi, “Shigellosis in Children from North India: A Clinicopathological Study,” J. Trop. Pediatr., Vol. 41, pp.303-307, 1995. [32] V. Vapnik, “The Nature of Statistical Learning Theory,” Springer-Verlag, 1995. L. Vincent and P. Soille, “Watersheds in digital spaces: an efficient algorithm based on immersion simulations,” IEEE Trans. Pattern Anal. Mach. Intell., Vol.13, pp.583-598, 1991. [33] L. Vincent and P. Soille, “Watersheds in digital spaces: an efficient algorithm based on immersion simulations,” IEEE Trans. Pattern Anal. Mach. Intell., Vol.13, pp.583-598, 1991. [34] C. Xu and J. L. Prince, “Snakes, Shapes, and Gradient Vector Flow,” IEEE Trans. Image Process., Vol.7, pp.359-369, 1998. [35] S. F. Yang-Mao, “Object Contour Detection in Medical Images,” Ph. D. thesis, National Chung-Hsing University, R.O.C., 2007. [36] D. Zheng, Y. Zhao, and J. Wang, “An Efficient Method of License Plate Location,” Pattern Recognition Letters, Vol. 26, pp. 2431-2438, 2005. [37] Center of Disease Control, R.O.C., Legal Infectious Diseases - Understanding Diseases, August 24, 2007, website available at http://www.cdc.gov.tw/.zh_TW
dc.identifier.urihttp://hdl.handle.net/11455/19630-
dc.description.abstract近三十年來,數位影像處理技術被廣泛的應用在幾何變換、影像壓縮、影像增強、影像切割等方面。所謂的影像切割是將感興趣的部份從背景取出的一種技術。然而,切割影像在電腦視覺上是一個相當大的挑戰,因為它將深深影響往後影像識別的正確率。本篇論文運用一些影像處理技術於處理車牌偵測及細胞切割。 車牌偵測在車牌辨識系統中扮演著相當重要的角色。如果車牌能夠被準確的偵測,對於接下來的字元切割及字元辨識會有事半功倍的效果。在我們的觀察中,影像的照度(illumination)將會影響車牌偵測。因此本論文的目標之一是在複雜背景且拍攝於不同情境的影像中擷取一張以上的車牌。車牌偵測的方法包含六個步驟:(1) 將彩色影像轉換為灰階影像 (2)影像均化 (3)邊緣偵測 (4)檢查黑色象素比例(5)車牌確認(6)輸出車牌。實驗結果顯示,本論文提出的方法在GetRatio達到94%的正確率; 在GetRight擁有83%的正確率。 致病性的原生寄生蟲會使人類得到許多疾病,例如:霍亂、傷寒及阿米巴症等等。目前,數位影像被廣泛使用在醫學領域幫助醫生及病理學家分析病理學上的問題及診斷疾病。本論文提出一個具有準確切割能力的數位影像處理技術將原生寄生蟲從一張影像品質較差或擁有複雜背景的顯微影像中切割出來。在實驗結果中,此方法可以獲得96.64%的正確率。除此之外,在ME、RN、EFAE三個錯誤率計算當中,其值分別只有0.04、0.45及0.06。zh_TW
dc.description.abstractDigital image processing is a widely applied technology in recent thirty years. Geometric transformations, image compression, image enhancement, image segmentation are some of the most used digital image processing techniques. Image segmentation is employed to distinguish the region of interest (ROI) from background. However, segmenting image is a great challenge for computer vision because the accuracy of image segmentation highly affects the accuracy of followed image recognition. In this thesis, some image processing techniques are proposed to deal with license plate detection and cell segmentation. License plate detection plays an important role in license plate recognition (LPR) system. If license plates can be located exactly, the character segmentation and recognition can be implemented more precisely and efficiently. In our observation, the illumination affects the result of locating a license plate. One aim of this thesis is to extract more than one license plate from an image and to obtain the license plates in the image taken under different conditions. The proposed method includes six processes as follows: transferring color to grayscale, image equalization, edge detection, checking black pixel ratio, plate verification and output license plates. The experimental results show that the proposed method can gain 94% accuracy in GetRatio and 83% accuracy in GetRight. The pathogenic protozoan parasites can cause human to get many diseases, such as, cholera, typhoid fever, and amoebiasis, etc. Digital images are extensively applied to medical fields for doctors and pathologists to analyze pathological sections and further diagnose the disease. A digital image processing scheme is prosposed to segment protozoan parasites from protozoan parasite microscopic images. The proposed image processing scheme has precise segmentation ability even if the image is with poor quality or complex background. The experimental results show that the proposed scheme can gain 96.64% correct rate (TN+TP), and about 0.04, 0.45 and 0.06 of the average error rates: ME, RN and EFAE, respectively.en_US
dc.description.tableofcontentsContents............................................ i List of Figures..................................... iii List of Tables...................................... v Chapter 1 Introduction.............................. 1 1.1 Preface......................................... 1 1.2 Image quantization.............................. 3 1.3 Digital images .................................. 4 1.4 Image filtration................................ 5 1.5 Image segmentation.............................. 7 1.5.1 Multilevel thresholding.................... 8 1.5.2 Region-based segmentation.................. 9 1.5.3 Segmentation by Watersheds................. 10 1.5.4 Classification............................. 10 Chapter 2 Related Works............................. 12 2.1 Color image processing.......................... 12 2.2 Image enhancement............................... 13 2.2.1 Histogram equalization..................... 13 2.2.2 Local area enhancement..................... 14 2.3 Image binarization.............................. 15 2.3.1 Otsu's method............................. 15 2.3.2 Yasuo et al's method...................... 16 2.4 Edge detection.................................. 17 2.4.1 Sobel edge detection....................... 17 2.4.2 Canny edge detection....................... 18 2.5 Mathematical morphology......................... 18 2.6 License plate extraction........................ 19 2.7 Cell segmentation............................... 20 Chapter 3 An Effective License-Plate Detection Method for Overexposure and Complex Vehicle Images........... 22 3.1 Proposed method................................. 22 3.1.1 Transferring color to grayscale............ 22 3.1.2 Image equalization ......................... 24 3.1.3 Edge detection............................. 25 3.1.4 Checking black pixel ratio................. 26 3.1.5 Plate verification ........................ 28 3.2 Experimental results........................... 29 Chapter 4 A Cell Segmentation Scheme for Digital Protozoan Parasite Microscopic Images........................ 32 4.1 Proposed method................................ 32 4.1.1 Color space transforming.................. 32 4.1.2 Gamma equalization ........................ 33 4.1.3 Median-mean filter ........................ 35 4.1.4 Two-classes edge enhancement.............. 36 4.1.5 Two-means clustering method............... 36 4.1.6 Largest independent component detection... 38 4.2 Experiment results............................. 40 Chapter 5 Conclusions.............................. 43 Bibliography....................................... 45 List of Figures Fig.1.4-1 Mean filter mask ........................ 6 Fig.1.4-2 An example for median filter............ 7 Fig.1.5-1 A simple example of image thrsholding method 9 Fig.1.5-2 Connected component criteria............ 9 Fig.1.5-3 A basic neural network model............. 11 Fig.2.2-1 The gray-scale transformation function... 14 Fig.2.4-1 Sobel masks.............................. 17 Fig.2.6-1 The process of feature extraction stage... 20 Fig.3.1-1 The overview of the proposed method....... 23 Fig.3.1-2 The gray-level histogram of a brighter/ darker image and the gray-level histogram after performing equalization......................................... 24 Fig.3.1-3 Traditional histogram equalization/ equalization mapping with linear interpolation.................... 25 Fig.3.1-4 An example for revising the vertical size of a license plate........................................ 27 Fig.3.1-5 An example for revising the horizontal size of a license plate........................................ 27 Fig.3.1-6 Revise license plate...................... 27 Fig.3.1-7 The results of morphological process...... 28 Fig.3.1-8 A 4-neighbor structuring element.......... 28 Fig.3.1-9 Histogram of a binary license plate candidate ..................................................... 29 Fig.3.2-1 Original color image...................... 30 Fig.3.2-2 Grayscale image........................... 30 Fig.3.2-3 Equalization image........................ 30 Fig.3.2-4 Edge detection image (T1 = 200)........... 30 Fig.3.2-5 The results after checking black pixel ratio (T2 = 500)/ histogram analysis of plate erification/ results of plate verification.................................... 31 Fig.4.1-1 A digital protozoan parasite image of Entamoeba histolytica/ The result of applying gray-level transforming to the protozoan...................................... 33 Fig.4.1-2 A description of the low-bound and the up-bound in gamma equalization................................. 34 Fig.4.1-3 The results of gamma equalization using different parameters (α and γ)....................... 35 Fig.4.1-4 The result image of applying median-mean filter ..................................................... 35 Fig.4.1-5 The result of applying two-classes edge enhancement........................................... 36 Fig.4.1-6 The result of applying two-means clustering method................................................. 37 Fig.4.1-7 The scanning directions and referred neighbors of different scanning models.......................... 38 Fig.4.1-8 The largest independent components obtained from Fig. 4.1-6 in different index scanning models......... 39 Fig.4.1-9 The result obtained by combining Fig. 4.1-8 (a)- (d) with OR operation/ The result of applying inter-size filling method to former.............................. 40 Fig.4.1-10 The comparison between original and processed image................................................. 40 Fig.4.2-1 The original image/ the results obtained without equalization/ the results of using gamma equalization. 41 List of Tables Table.3.2-1 GetRatio in each image................... 31 Table.3.2-2 GetRight in each image................... 31 Table.3.2-3 Compare with Chen et al.'s method....... 31 Table.4.1-1 The means and ranges of TP, TN, FP and FN for the proposed scheme without equalization or with gamma equalization.......................................... 42 Table.4.1-2 The means and ranges of ME, RN and EFAE for the proposed scheme without equalization or with gamma equalization......................................... 42zh_TW
dc.language.isoen_USzh_TW
dc.publisher資訊科學與工程學系所zh_TW
dc.relation.urihttp://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0005-2007200912152100en_US
dc.subject車牌辨識zh_TW
dc.subjectLicense plate recognition (LPR)en_US
dc.subject邊緣偵測zh_TW
dc.subject形態學zh_TW
dc.subject原生寄生蟲zh_TW
dc.subject細胞切割法zh_TW
dc.subjectgamma均化zh_TW
dc.subjecttwo-means 分群法zh_TW
dc.subjectedge detectionen_US
dc.subjectmorphologyen_US
dc.subjectprotozoan parasitesen_US
dc.subjectcell segmentation schemeen_US
dc.subjectgamma equalizationen_US
dc.subjecttwo-means clusteringen_US
dc.title影像切割之研究及其應用zh_TW
dc.titleA Study on Image Segmentations and Applicationsen_US
dc.typeThesis and Dissertationzh_TW
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.languageiso639-1en_US-
item.openairetypeThesis and Dissertation-
item.grantfulltextnone-
item.fulltextno fulltext-
item.cerifentitytypePublications-
Appears in Collections:資訊科學與工程學系所
Show simple item record
 

Google ScholarTM

Check


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