請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/41063
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 林巍聳(Wei-Song Lin) | |
dc.contributor.author | Yu-Wei Huang | en |
dc.contributor.author | 黃昱瑋 | zh_TW |
dc.date.accessioned | 2021-06-14T17:14:42Z | - |
dc.date.available | 2008-08-04 | |
dc.date.copyright | 2008-08-04 | |
dc.date.issued | 2008 | |
dc.date.submitted | 2008-07-25 | |
dc.identifier.citation | [Arturo De La Escalera, 1997] M. A. S. Arturo De La Escalera, 'Road Traffic Sign Detection and Classification,' IEEE TRANSACTION ON INDUSTRIAL ELECTRONICS 1997, vol. 44, no. 6.
[Chen, 2002] Y. Chen, 'A region-based fuzzy feature matching approach to content-basedimage retrieval,' IEEE Transactions on Pattern Analysis and Machine Intelligence 2002, vol. 24, no. 9, pp. 1252-1267. [D. Nauck, 1994] R. K. D. Nauck, ' NEFCON-I: an X-Window based simulator for neural fuzzy controllers,' in 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on Neural Networks, Orlando, FL, USA, 1994, pp. 1638-1643. [F. Hoppner, 1999] F. K. F. Hoppner, R. Kruse, T. Runkler, Fuzzy cluster analysis: methods for classification, data analysis and image recognition. John Wiley & Sons, 1999. [Fang, 2007] C. H. Fang, 'Intention-oriented Computational Visual Attention and Shape Recognition,' Doctor Thesis, Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan, 2007. [H.R. Berenji, 1992] P. K. H.R. Berenji, 'Learning and tuning fuzzy logic controller through reinforcements,' IEEE TRANSACTIONS ON NEURAL NETWORKS 1992, vol. 3, no. 5. [Hu, 2004] W. Hu, 'A Survey on visual surveillance of object motion and behaviors,' IEEE Transactions on Systems, Man, and Cybernetics - Part C: Applications and Reviews 2004 2004, vol. 34, no. 3, pp. 334-358. [Jang, 1993] R. Jang, 'ANFIS: Adaptive-Network-Based Fuzzy Inference System,' IEEE TRANSACTION ON SYSTEMS, MAN, AND CYBERNETICS 1993, vol. 23, no. 3. [Jung, 2004] C. R. Jung, 'Rectangle Detection based on a Windowed Hough Transform,' in Computer Graphics and Image Processing, 2004. Proceedings. 17th Brazilian Symposium on, 2004, pp. 113-120. [Koch, 1985] C. Koch, 'Shifts in selective visual attention: towards the underlying neural circuitry,' Human Neurobiology 1985, vol. 4, no. 4, pp. 219-227. [Kohonen, 1988] T. Kohonen, 'Self-Organizing Feature Maps,' in Self-Organization and Associative Memory: Berlin, Germany: Springer-Verlag, 1988, p. 132. [L. Itti, 1998] C. K. L. Itti, 'A model of saliency-based visual attention for rapid scene analysis,' IEEE Transactions on Pattern Analysis and Machine Intelligence 1998, vol. 20, no. 11, p. 1254. [Lin, 1991] C. T. Lin, 'Neural-Network-Based Fuzzy Logic Control and Decision System ' IEEE Transactions on Computers 1991, vol. 40, no. 12. [Lin, 2006] W. S. Lin, 'Computational model of intention-oriented visual attention,' in Proceedings of 2006 IEEE International Conference on System, Man, and Cybernetics (SMC), Taipei, Taiwan, 2006, pp. 2357-2361. [Liu, 2004] A.-T. Liu, 'Autonomous visual perception with cellular neural networks,' Master Thesis, Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan, 2004. [Milanese, 1994] R. Milanese, 'Feature binding through synchronized neuronal oscillations: A preliminary study,' 1994. [P. J. Burt, 1983] E. H. A. P. J. Burt, 'The Laplacian Pyramid as a Compact Image Code,' IEEE Transactions on Communacations, April 1983 1983, vol. COM-31, no. 4. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/41063 | - |
dc.description.abstract | 人的視覺可以根據意向在視野中尋找特定的目標,實質上這是一個結合影像訊息和心理意願的視覺智能,而意向式視注覺演算模型就是實現這個視覺智能的具體方法。本研究的目的是發展具有學習能力的意向式視注覺演算模型,讓意向可以用影像樣本表示,而系統可以自動從樣本萃取代表意向的模糊邏輯規則,做為蒐尋特定目標的依據。有學習能力的意向式視注覺演算模型會從影像中萃取亮度、色澤、形狀等特徵,再用中央與周圍對比機制篩選特徵突顯的區塊,模糊類神經網路則會根據代表意向的模糊邏輯規則,從突顯的區塊中選出符合意向的標的;意向式視注覺演算模型是仿效既有的方法,而有學習能力的意向式視注覺演算模型則是本研究的主要貢獻,使系統可以自動從影像特徵萃取代表意向的模糊邏輯規則,並用以蒐尋符合意向的目標。有學習能力的意向式視注覺演算模型可應用於影像內容蒐尋,本研究以輔助駕駛人蒐尋路標目標的實驗展示其可行性。 | zh_TW |
dc.description.abstract | Human vision can intentionally find a target in the view. Technologically, this ability is a data- and intention-driven mechanism, and the intention oriented computational visual attention (ICVA) model attempts to imitate it by computational intelligence. This research contributes to enabling the ICVA model with learning ability so as to acquire or change intention according to assigned image samples. This innovative design is called the self-learning ICVA model which contains a neuro-fuzzy network to learn intention from image samples. A well-trained self-learning ICVA model can find interested objects in images by extracting attentive areas and matching them with intention expressed by fuzzy rules. Image features are extracted from intensity, color hue, shape and symmetry channels. Attentive areas are determined by implementing the center-surround mechanism. Intention or interested image content is assigned by image samples. By extracting fuzzy rules from image samples, the self-learning ICVA model acquires or changes the intention. The whole design is verified by constructing an intelligent road sign detection system. Experimental results show the system succeeds in learning and seeking image content with rectangular road signs. | en |
dc.description.provenance | Made available in DSpace on 2021-06-14T17:14:42Z (GMT). No. of bitstreams: 1 ntu-97-R95921006-1.pdf: 2929077 bytes, checksum: acfb1550429785cbd110aff06f5e8cd3 (MD5) Previous issue date: 2008 | en |
dc.description.tableofcontents | 應用於學習和追尋影像內涵之意向視注覺模型 I
誌 謝 II 中文摘要 III Abstract IV Content V List of Figures VII List of Tables IX Chapter 1 Introduction 1 1.1 Background and motivation 1 1.2 Contributions 5 1.3 Organization 7 Chapter 2 Preliminaries of Visual Attention and Computational Visual Attention 8 2.1. Introduction 8 2.2. Human Vision System 9 2.2.1. Retina 9 2.2.2. Lateral Geniculate Nucleus (LGN) 11 2.2.3. Contrary Mechanism about Color 12 2.3. Typical Computational Visual Attention models 13 2.3.1. Koch & Ullman’s model 13 2.3.2. Milanese’s model 15 2.3.3. Itti’s model 15 2.4. Saliency Detection by CVA model 18 2.4.1. Feature Extraction 18 2.4.1.1. Color Space 18 2.4.1.2. Intensity Feature Maps 24 2.4.1.3. Color Feature Maps 24 2.4.1.4. Orientation Feature Maps 25 2.4.2. Image Gaussian Pyramid 26 2.4.3. Center-Surround Mechanism 30 2.4.4. Global Nonlinear Normalization Operator 32 2.5. Intention-oriented Computational Visual Attention model 34 2.5.1. Intention for Visual Attention and ICVA model 34 2.5.2. Intention Feature Maps 37 Chapter 3 Self-Learning Intention-oriented Visual Attention model 39 3.1. Introduction 39 3.2. Framework of the Self-Learning ICVA model 40 3.3. Feature Extraction 43 3.4. Intention-inside Neuro-Fuzzy Network 51 3.5. Learning Algorithm of Intention-inside Neuro-Fuzzy Network 57 3.6. Attentive Area Generator 67 Chapter 4 Intelligent Road Sign Detection System 71 4.1 Design of Intelligent Road Sign Detection System 71 4.2 Experiment I: Detecting and Locating Green Rectangular Road Sign 81 4.3 Experiment II: Detecting Multiple Kinds of Road Signs 88 4.4 Analysis and Discussion of Experiment Data 92 Chapter 5 Conclusion and Future Work 98 Reference 101 | |
dc.language.iso | en | |
dc.title | 應用於學習和追尋影像內涵之意向視注覺模型 | zh_TW |
dc.title | Intention-oriented visual attention model for learning and seeking image content | en |
dc.type | Thesis | |
dc.date.schoolyear | 96-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 邱榮輝(Jung-Hui Chiu),陳文良(Wen-Liang Chen),鍾鴻源(Hung-Yuan Chung) | |
dc.subject.keyword | 視覺,視注覺,類神經網路,影像蒐尋,模糊邏輯, | zh_TW |
dc.subject.keyword | machine vision,visual attention,neural network,image content searching,fuzzy logic, | en |
dc.relation.page | 102 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2008-07-28 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
顯示於系所單位: | 電機工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-97-1.pdf 目前未授權公開取用 | 2.86 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。