跳到主要內容

臺灣博碩士論文加值系統

(3.235.120.150) 您好!臺灣時間:2021/08/06 02:53
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:李品萱
研究生(外文):Pin-Xuan Lee
論文名稱:運用影像處理技術之仿冒中文字跡辨識
論文名稱(外文):Forensic Writer Verification on Chinese Characters by Image Processing Techniques
指導教授:丁建均丁建均引用關係
指導教授(外文):Jian-Jiun Ding
口試委員:葉敏宏郭景明許文良
口試日期:2015-01-05
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:電信工程學研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2015
畢業學年度:103
語文別:英文
論文頁數:93
中文關鍵詞:字跡辨識高斯差哈里斯角點尺度不變特徵轉換方向性亮度區塊K均值分群法支持向量機對數賈伯特徵不變矩灰階共生矩陣加權歐氏距離平方
外文關鍵詞:writer verificationdifference of GaussianHarris cornerscale-invariant feature transformoriented intensity patchK-means clusteringsupport vector machinelog-Gabor featuremoment invariantgray level co-occurrence matrixweighted squared Euclidean distance
相關次數:
  • 被引用被引用:1
  • 點閱點閱:224
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
字跡是一種富含資訊的生物識別特徵而字跡辨識也在法務鑑定上扮演非常重要的角色。然而,由於行為特性導致個體字跡的變異程度大,使得字跡辨識仍然是一個具有挑戰性的研究題目。在本篇論文中,我們將會提出兩種能增加辨識率的中文字跡辨識系統。
在第一個方法中,我們利用區域特徵和支持向量機來進行字跡辨識。首先藉由組合各種偵測子和描述子,包括高斯差、哈里斯角點、尺度不辨特徵轉換描述子以及方向性亮度區塊描述子,來產生區域特徵。由於每張圖片所找出的特徵點數目不同,因此需用K均值分群法先建立編碼簿。然後根據詞袋模型,每份手寫字跡便能以編碼頻率直方圖表示,進而成為支持向量機的輸入特徵向量。
之後我們也開始研究全域特徵在字跡辨識的應用,所以另外一個提出的方法則是以全域特徵作為基礎。這個系統利用了對數賈伯特徵、進階不變矩和灰階共生矩陣的擷取特徵,並得到比前者更佳的辨識率。藉由這些特徵的結合,這個系統在傳統辨識問題上顯現出更卓越的穩健性。除此之外,我們也提出了一個更有彈性的分類架構。雖然支持向量機提供了準確的結果,但卻為訓練資料的數量所限。為了避免在訓練資料不足或是不平衡的情況下發生過度擬合,另外一個分類方法僅以加權歐氏距離平方作為辨識基準。模擬結果顯示,我們提出的字跡辨識系統在有/無搭配支持向量機的架構下分別能達到92.7% 和83.5%的準確度,而這也超越了其他現有的辨識方法,包括區域二元模式、區域方向模式、賈伯特徵、分段筆劃直方圖以及分段曲度編碼。

Handwriting is an informative kind of biometrics and writer verification plays a very important role in forensics. However, writer verification remains a challenging topic due to the large variations caused by the behavioral trait of individuals. In this thesis, two systems of writer verification are proposed to improve verification accuracy.
The first method is to perform writer verification with local features and the support vector machine. These local features are generated by different combinations of detectors and descriptors, including the difference of Gaussian, the Harris corner, the SIFT descriptor and the oriented intensity patch. Since the amount of keypoints are various, a construction of codebook is required. K-means clustering is applied to build the codebook. Then, by the bag-of-word model, each handwriting image can be represented by a histogram with the codewords being indices. The histograms are the input feature vectors used for the support vector machine, which is a famous technique in machine learning.
Later, global features are also explored in this research. So another method based on global features is proposed. This verification performs even better by using log-Gabor features, some advanced moments and features extracted from gray level co-occurrence matrices. By combining these features, the system shows superior robustness for traditional verification problems. Besides, a more flexible classification framework is proposed. Though the support vector machine leads to accurate results, it is confined to the amount of training data. To prevent overfitting, another classification method based on the weighted squared Euclidean distance is devised for the case of insufficient or unbalanced training data. From the results of simulation, the accuracies can reach about 92.7% and 83.5% for the proposed framework with/without the support vector machine, respectively, which outperform other popular identification or verification methods, including the local binary pattern, the local directional pattern, Gabor features, the stroke fragment histogram and the curve fragment code.

口試委員會審定書 #
誌謝 i
中文摘要 ii
ABSTRACT iv
CONTENTS vi
LIST OF FIGURES ix
LIST OF TABLES xii
Chapter 1 Introduction 1
1.1 Background 1
1.2 Organization 2
Chapter 2 Fundamentals─Overview of Common Feature Extraction Methods 3
2.1 Gabor Wavelet 3
2.2 Local Pattern 7
2.2.1 Local Binary Pattern (LBP) 7
2.2.2 Local Directional Pattern (LDP) 8
2.3 Basic Moment Features 10
2.4 Stroke Fragment Histogram (SFH) 12
2.5 Curve Fragment Code (CFC) 16
2.6 Scale-Invariant Feature Transform (SIFT) 19
Chapter 3 Fundamentals─Overview of Common Classification Methods 22
3.1 Weighted Euclidean Distance 22
3.2 K-Means Clustering 24
3.3 Self-Organizing Map (SOM) 26
3.4 Principal Component Analysis (PCA) 28
3.5 Discrete Cosine Transform (DCT) 30
3.6 Support Vector Machine (SVM) 31
Chapter 4 Introduction of the Collected Database and Experimental Setup 34
4.1 The Collected Database 34
4.2 Noise Removal 36
4.3 Rotation Adjustment 37
4.4 Segmentation 38
4.5 Experimental Setup 39
Chapter 5 Proposed Writer Verification System Based on Local Features and the Support Vector Machine 40
5.1 Introduction 40
5.2 Related Work 41
5.3 Overview of the Proposed Framework 42
5.4 Local Features 43
5.4.1 Detectors and Descriptors 43
5.4.2 Normalized Keypoint Location 47
5.5 Bag-of-Word (BoW) Model 47
5.6 Support Vector Machine for Classification 49
5.7 Simulation Results 50
5.8 Summary 57
Chapter 6 Proposed Writer Verification System Based on Global Features and the Adaptive Classification Method 58
6.1 Introduction 58
6.2 Related Work 59
6.3 Overview of the Proposed Framework 60
6.4 Global Features 61
6.4.1 Log-Gabor Filtering 61
6.4.2 Advanced Moment Features 63
6.4.3 Gray Level Co-occurrence Matrix (GLCM) 66
6.5 Adaptive Method for Classification 70
6.6 Simulation Results 73
6.6.1 Typical SVM Classification 73
6.6.2 Adaptive WSED Classification 80
6.7 Summary 84
Chapter 7 Conclusions and Future Work 85
7.1 Conclusions 85
7.2 Future Work 86
REFERENCE 87
PUBLICATION 93


A.Feature Extraction Basics
[1]Cho, Yong Cheol Peter, et al. "Exploring Gabor filter implementations for visual cortex modeling on FPGA." Field Programmable Logic and Applications (FPL), 2011 International Conference on. IEEE, pp. 297-302, 2011.
[2]Manjunath, Bangalore S., and Wei-Ying Ma. "Texture features for browsing and retrieval of image data." Pattern Analysis and Machine Intelligence, IEEE Transactions on 18.8 (1996): 837-842.
[3]Winston H. Hsu. "Texture and shape for image retrieval and multimedia analysis and indexing." National Taiwan University, 2013.
[4]Ojala, Timo, Matti Pietikäinen, and David Harwood. "A comparative study of texture measures with classification based on featured distributions." Pattern recognition 29.1 (1996): 51-59.
[5]Ferrer, Miguel A., Aythami Morales, and J. F. Vargas. "Off-line signature verification using local patterns." Telecommunications (CONATEL), 2011 2nd National Conference on. IEEE, pp. 1-6, 2011.
[6]Jabid, Taskeed, Md Hasanul Kabir, and Oksam Chae. "Facial expression recognition using local directional pattern (LDP)." Image Processing (ICIP), 2010 17th IEEE International Conference on. IEEE, pp. 1605-1608, 2010.
[7]Tang, Youbao, Xiangqian Wu, and Wei Bu. "Offline text-independent writer identification using stroke fragment and contour based features." Biometrics (ICB), 2013 International Conference on. IEEE, pp. 1-6, 2013.
[8]Wang, Xianliang, Xiaoqing Ding, and Hailong Liu. "Writer identification using directional element features and linear transform." 2013 12th International Conference on Document Analysis and Recognition. Vol. 2, pp. 942-942. IEEE Computer Society, 2003.
[9]Ghiasi, Golnaz, and Reza Safabakhsh. "Offline text-independent writer identification using codebook and efficient code extraction methods." Image and Vision Computing 31.5 (2013): 379-391.
[10]Contour Tracing http://www.imageprocessingplace.com/downloads_V3/root_downloads/tutorials/contour_tracing_Abeer_George_Ghuneim/moore.html.
[11]Schomaker, Lambert, Marius Bulacu, and Katrin Franke. "Automatic writer identification using fragmented connected-component contours." Frontiers in Handwriting Recognition, 2004. IWFHR-9 2004. Ninth International Workshop on. IEEE, pp. 185-190, 2004.
[12]Lowe, David G. "Distinctive image features from scale-invariant keypoints."International journal of computer vision 60.2 (2004): 91-110.
B.Classification Basics
[13]Cash, Glenn L., and Mehdi Hatamian. "Optical character recognition by the method of moments." Computer Vision, Graphics, and Image Processing 39.3 (1987): 291-310.
[14]Greenacre, Michael. Correspondence analysis in practice. CRC Press, 2010.
[15]Ming-Sui Lee, "Digital Image Processing" National Taiwan University, 2013.
[16]Kohonen’s Self-Organizing Map in Matlab
http://home.wlu.edu/~levys/software/som/
[17]Kohonen, Teuvo. "The self-organizing map." Neurocomputing 21.1 (1998): 1-6.
[18]A Tutorial on Principal Component Analysis http://www.cs.otago.ac.nz/cosc453/student_tutorials/principal_components.pdf
[19]PCA-Principal Component Analysis
http://www.nlpca.org/pca_principal_component_analysis.html
[20]Ahmed, Nasir, T. Natarajan, and Kamisetty R. Rao. "Discrete cosine transform." Computers, IEEE Transactions on 100.1 (1974): 90-93.
[21]Cortes, Corinna, and Vladimir Vapnik. "Support-vector networks." Machine learning 20.3 (1995): 273-297.
[22]Hsu, Chih-Wei, Chih-Chung Chang, and Chih-Jen Lin. "A practical guide to support vector classification." (2003).
C.Writer Identification
[23]Bensefia, Ameur, et al. "Writer identification by writer''s invariants." Frontiers in Handwriting Recognition, 2002. Proceedings. Eighth International Workshop on. IEEE, pp. 274-279, 2002.
[24]Jain, Rajiv, and David Doermann. "Offline writer identification using k-adjacent segments." Document Analysis and Recognition (ICDAR), 2011 International Conference on. IEEE, pp. 769-773, 2011.
[25]Schomaker, Lambert, Katrin Franke, and Marius Bulacu. "Using codebooks of fragmented connected-component contours in forensic and historic writer identification." Pattern Recognition Letters 28.6 (2007): 719-727.
[26]Woodard, Jeffrey, et al. "Writer recognition of Arabic text by generative local features." Biometrics: Theory Applications and Systems (BTAS), 2010 Fourth
IEEE International Conference on. IEEE, pp. 1-7, 2010.
[27]Coetzer, Johannes, Ben M. Herbst, and Johan A. du Preez. "Offline signature verification using the discrete radon transform and a hidden Markov model."EURASIP Journal on Applied Signal Processing 2004 (2004): 559-571.
[28]Yilmaz, Mustafa Berkay, et al. "Offline signature verification using classifier combination of HOG and LBP features." Biometrics (IJCB), 2011 International Joint Conference on. IEEE, pp. 1-7, 2011.
[29]Imdad, Asim, et al. "Writer Identification Using Steered Hermite Features and SVM." ICDAR., pp. 839-843, 2007.
[30]Brown, Matthew, Richard Szeliski, and Simon Winder. "Multi-image matching using multi-scale oriented patches." Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. Vol. 1, pp. 510-517 IEEE, 2005.
[31]Sivic, Josef, and Andrew Zisserman. "Video Google: A text retrieval approach to object matching in videos." Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on. IEEE, pp. 1470-1477, 2003.
D.Signature Verification
[32]Deng, Peter Shaohua, et al. "Wavelet-based off-line handwritten signature verification." Computer vision and image understanding 76.3 (1999): 173-190.
[33]Vargas, Jesus F., et al. "Offline signature verification based on pseudo-cepstral coefficients." Document Analysis and Recognition, 2009. ICDAR''09. 10th International Conference on. IEEE, pp. 126-130, 2009.
[34]Parodi, Marianela, Juan C. Gomez, and Abdel Belaïd. "A circular grid-based rotation invariant feature extraction approach for off-line signature verification."Document Analysis and Recognition (ICDAR), 2011 International Conference on. IEEE, pp. 1289-1293, 2011.
[35]He, Z. Y., and Y. Y. Tang. "Chinese handwriting-based writer identification by texture analysis." Machine Learning and Cybernetics, 2004. Proceedings of 2004 International Conference on. Vol. 6, pp. 3488-3491, IEEE, 2004.
[36]Sigari, Mohamad Hoseyn, Muhammad Reza Pourshahabi, and Hamid Reza Pourreza. "Offline handwritten signature identification and verification using multi-resolution gabor wavelet." International Journal of Biometric and Bioinformatics 5 (2011).
[37]Ferrer, Miguel A., et al. "Robustness of offline signature verification based on gray level features." Information Forensics and Security, IEEE Transactions on7.3 (2012): 966-977.
[38]Swanepoel, Jacques P., and Johannes Coetzer. "Off-line signature verification using flexible grid features and classifier fusion." Frontiers in Handwriting Recognition (ICFHR), 2010 International Conference on. IEEE, pp. 297-302, 2010.
[39]Field, David J. "Relations between the statistics of natural images and the response properties of cortical cells." JOSA A 4.12 (1987): 2379-2394.
[40]What Are Log-Gabor Filters and Why Are They Good?
http://www.csse.uwa.edu.au/~pk/research/matlabfns/PhaseCongruency/Docs/convexpl.html
[41]Chim, Y. C., Ashraf A. Kassim, and Y. Ibrahim. "Character recognition using statistical moments." Image and vision Computing 17.3 (1999): 299-307.
[42]Hu, Ming-Kuei. "Visual pattern recognition by moment invariants." Information Theory, IRE Transactions on 8.2 (1962): 179-187.
[43]Flusser, Jan, and Tomas Suk. "Pattern recognition by affine moment invariants." Pattern recognition 26.1 (1993): 167-174.
[44]Tsirikolias, K., and Basil G. Mertzios. "Statistical pattern recognition using efficient two-dimensional moments with applications to character recognition."Pattern Recognition 26.6 (1993): 877-882.
[45]Haralick, Robert M., Karthikeyan Shanmugam, and Its'' Hak Dinstein. "Textural features for image classification." Systems, Man and Cybernetics, IEEE Transactions on 6 (1973): 610-621.
[46]Matlab Documentation on Function “graycomatrix”
http://www.mathworks.com/help/images/ref/graycomatrix.html
[47]Vargas, J. F., et al. "Off-line signature verification based on grey level information using texture features." Pattern Recognition 44.2 (2011): 375-385.
[48]Haralick, Robert M. "Statistical and structural approaches to texture."Proceedings of the IEEE 67.5 (1979): 786-804.
E.Source Code
[49]Matlab Implementation of Log-Gabor Filtering
http://www.csse.uwa.edu.au/~pk/research/matlabfns/
[50]LIBSVM-A Library for Support Vector Machines
http://www.csie.ntu.edu.tw/~cjlin/libsvm/
[51]Matlab Implementation of Gabor Filter Bank
Haghighat, Mohammad, Saman Zonouz, and Mohamed Abdel-Mottaleb. "Identification Using Encrypted Biometrics." Computer Analysis of Images and Patterns. Springer Berlin Heidelberg, pp. 440-448, 2013.
[52]Boundary Tracing Based on Moore’s Algorithm
http://www.mathworks.com/matlabcentral/fileexchange/27639-boundary-tracing-using-the-moore-neighbourhood
[53]Kohonen’s Self-Organizing Map in Matlab
http://home.wlu.edu/~levys/software/som/
[54]Matlab Implementation of Local Binary Patterns (LBP), Local Directional Patterns (LDP) and Local Derived Patterns (LDerivP)
http://www.gpds.ulpgc.es/download/index.htm

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top