近半世紀來，由於工商業的快速發展，今日的工業已經具有先進自動化技術與卓越製造能力。然而生產線效能的提升，往往也可能在極短的時間內會生產出數量龐大的瑕疵品，人工檢測不但費時費力且容易造成遺漏。近年來機器視覺的技術逐漸被應用於自動化檢測的系統，一種以紋理分析理論為基礎之瑕疵偵測與定位系統，多年來，已經引起廣泛且深入的研究與發展。
影像瑕疵的偵測及定位主要是利用樣板比對的方式，透過比對無瑕疵樣板與待測影像的特徵差異，以達到瑕疵定位的目的。在本論文中分別以紋理分析之統計法，包括灰階共生矩陣與鄰近灰階相依矩陣，以及以傅立葉轉換為基礎的頻譜法來分析影像的紋理特徵，並發展瑕疵偵測定位系統。為了改善因待測影像的偏轉而造成瑕疵偵測性能大幅降低的問題，本論文也更進一步地提出以相位相關法(Phase correlation)來估測待測影像偏轉的角度並予以補償。
本論文中將採用多種不同紋理及瑕疵的影像來驗證瑕疵偵測與定位系統的性能，其中包括生活中常見之人造織品雙線瑕疵、LCD面板瑕疵、油污瑕疵以及機械加工中常見的刮痕瑕疵、凹陷瑕疵與孔洞瑕疵。實作結果顯示加入相位相關法來補償待測影像偏轉的角度，可以有效提升瑕疵偵測與定位系統的整體性能。

The rapid development in automation techniques in the last few decades has drastically changed the land scope of the industrial world. The highly automated machines can produce with previously unimaginable speed. One of the problems with this production speed is that if there is any fault on any part of the production process and if it is not detected soon enough, quite a lot of defected product can be spewed out of from the machine in a very short while, and hence causes tremendous losses. Frequent human inspection can partly relieve only part of the problem, because it needs highly trained skills and is generally not very reliable. The recent development in machine vision techniques seems able to provide a more reliable alternative. Many research efforts have been devoted in this area, and many encouraging results has been published. As a result, to design a defect detection and localization system which based on the texture analysis theory is possible nowadays.
This thesis is to design a system is to detect and locate defects by comparing the pre-selected reference and the input image. Many traditional texture analysis techniques such as statistics-based method (namely, GLCM and NGLDM) and Fourier analysis based method are thoroughly examined, analyzed. Based on our findings, we developed a phase correlation technique which can handle image rotation problem effectively. An hence the system we designed is able to detect and locate defects efficiently even if the input image is rotated.

[1] Gosta H. Granlund , Hans Knutsson, “Signal Processing for Computer Vision” ,1995

[2] Sklansky ,J., “Image Segmentation and Feature Extraction” , IEEE Transaction on Systems, Man, and Cybernetics,1978.

[3] Haralick, R.M., “Statistical and structural Approaches to Texture ”, Proceedings of the IEEE, VOLUME 67, NO. 5, MAY 1979.

[4] Fumiaki ,Saburo, ”Computer Analysis of Visual Textures” 1990

[5] C. H. Chen , L. F. Pau , P. S. P. Wang(eds) ”The Handbook of Pattern Recognition and Computer Vision(2nd Edition)” , pp. 207-248 , World Scientific Publishing Co. , 1998.

[6] Ahmet Latif Amet, Aysin Ertüzün, Aytül Erçil “Texture Defect Detection Using Subband Domain Co-Occurrence Matrices” , IEEE Southwest Symposium,1998

[7] Lee Hok Siew , Robert M. Hodgson , Errol J. Wood ”Texture Measures for Carpet Wear Assessment” , IEEE Transaction on Pattern Analysis and Machine Intelligence , VOLUME 10 , NO. 1 , JANUARY 1988.

[8] D. Mery , M. A. Berti ”Automatic Detection of Welding Defects Using Texture Features” International Symposium on Computerized Tomography and Image Processing for Industrial Applications in Radiology , Berlin , June 23-25 , 2003.

[9] Chi-ho Chen , Granthan K. H. Pang “Fabric Defect Detection by Fourier Analysis”, IEEE Transactions on Industry Application , VOLUME 36 , NO.5 , 2000.

[10] Z. Peng , T. B. Kirk “Two-dimensional Fast Fourier Transform and Power Spectrum for Wear Particle Analysis”, IEEE Transactions on Industry Application , Tribology International , VOLUME 30 , NO.8 , July , 1997.

[11] Leen Kiat Soh , Costas Tsatsoulis “Texture Analysis of SAR Sea Ice Imagery Using Gray Level Co-Occurrence Matrices ”, IEEE Transactions on Geoscience and Remote Sensing , VOLUME 37 , NO.2 , March , 1999.

[12] Umasankar Kandaswamy , Donald A. Adjeroh , M. C. Lee “Efficient Texture Analysis of SAR Imagery”, IEEE Transactions on Geoscience and Remote Sensing , VOLUME 43 , NO.9 , March , 2005.

[13] Mari Partio, Bargdan Cramariuc “Rock Texture Retrieval Using Gray Level Co-Occurrence Matrix”, Proceedings of the 5th Nordic Signal Processing Symposium, 2002.

[14] Christodoulos I. Christodoulou , Silas C. Michaelides , Constantinos S. Pattichis “Multifeature Texture Analysis for the Classification of Clouds in Satellite Imagery ”, IEEE Transactions on Geoscience and Remote Sensing , VOLUME 41 , NO.11 , November , 2005.

[15] Anantha Murali , William V. Stoecker , Randy H. Moss “Detection of Solid Pigment in Dermatoscopy Images Using Texture Analysis ”, Skin Research and Technology , VOLUME 6 , November , 2000.

[16] Otto C. Rotunno Filho , Paul M. Treitz “Texture Processing of Synthetic Aperture Radar Data Using Second-Order Spatial Statistics ”, Computers and Geoscience , VOLUME 22 , NO.1 , pp. 27-34 , 1996.

[17] Di Ruberto , C. Rodriguez , G. Vitulano “Image Segmentation by Texture Analysis ”, Image Analysis and Processing , pp. 376-381 , 1999.

[18] Dengsheng Zhang , Guojun Lu , “Study and Evaluation of Different Fourier Methods for Image Retrieval ”, Image and Vision Computing , VOLUME 23 , NO.1 , January , 2005.

[19] D.-M. Tsai , C.-Y. Hsieh , “Automated Surface Inspection for Directional Textures ”, Image and Vision Computing , VOLUME 18 , April , 1999.

[20] Du-Ming Tsai , Tse-Yun Huang , “Automated Surface Inspection for Statistical Textures ”, Image and Vision Computing , VOLUME 21 , January , 2003.

[21] Terry Cacelli , Bela Julesz “Psychophysical Evidence for Global Feature Processing in Visual Texture Discrimination ”, Journal of the Optical Society of America , VOLUME 69 , NO.5 , May , 1975.

[22] Jon R. Berry , John Goutsias , “A Comparative Study of Measures for Maximum Likelihood Texture Classification”, IEEE Transactions on Systems , Man , and Cybernetics , VOLUME 21 , NO.1 , January , 1991.

[23] C. D. Kuglin , D. C. Hines , “The Phase Correlation Image Alignment Method”, Proc IEEE Conf. Cybernetics and Society , pp. 163-165 , September , 1975.

[24] B. Srinivasa Reddy , B. N. Chatterji , “An FFT-Based Technique for Translation , Rotation , and Scale-Invariant Image Registration”, IEEE Transactions on Image Processing , VOLUME 5 , NO.8 , August , 1991.

[25] Yosi Keller , Amir Averbuch ,Moshe Israeli , “Pseudopolar-Based Estimation of Large Translations , Rotations , and Scalings in Images”, IEEE Transactions on Image Processing , VOLUME 14 , NO.1 , January , 2005.

[26] Yosi Keller , Yoel Shkolnisky , Amir Averbuch , “The Angular Difference Function and Its Application to Image Registration”, IEEE Transactions on Pattern Analysis and Machine Intelligence , VOLUME 27 , NO.6 , June , 2005.

[27] A. Averbuch , Y. Keller , “FFT Based Image Registration”, IEEE International Conference on Acoustic , Speech , and Signal Processing , Orlando: IEEE Press , 2002.

[28] David G. Barber , Mohammed E. Shokr , “A Comparison of Second-Order Classifiers for SAR Sea Ice Discrimination”, Photogrammetric Engineering and Remote Sensing , VOLUME 59 , NO.9 , pp. 1397-1408 , September , 1993.

[29] Ajay Kumar , Grantham K. H. Pang , “Defect Detection in Textured Material Using Optimized Filters”, IEEE Transactions on Systems , Man , and Cybernetics – Part B: Cybernetics , VOLUME 32 , NO.5 , October , 2002.

[30] Paul M. Treitz , Otto Rotunno Filho , “Textural Processing of Multi-Polarization SAR for Agricultural Crop Classification”, IEEE Transactions on Geoscience and Remote Sensing , VOLUME 4 , May , 1996.

[31] 陳普中，“紋理分析於瑕疵定位及影像檢索之研究” ，國立台灣科技大學電機工程所碩士論文，七月，2005.

[32] 栗宇平，“混合空間域與頻域之影像套合” ，國立台灣科技大學電機工程所碩士論文，七月，2005.

[33] 李坤龍，“一個基於傅立葉轉換及小波轉換之紋理分析的研究” ，國立交通大學資訊科學系博士論文，六月，2002.

[34] 唐德誠，“灰階共生矩陣於多波段多極化SAR影像分類之研究” ，國防大學中正理工學院軍事工程研究所碩士論文，六月，2002.

[35] Alan V. Oppenheim , Ronald W. Schafer , “Discrete-Time Signal Processing”, Prentice Hall.

[36] Athanasios Papoulis , S. Unnikrishna Pillai , “Probability , Random Variables and Stochastic Processes”, McGraw Hill , 2002.

[37] David A. Forsyth , Jean Ponce , “Computer Vision – A Modern Approach”, Prentice Hall , 2003.

[38] Rafael C. Gonzalez , Richard E. Woods , “Digital Image Processing”, Prentice Hall , 1993.