臺灣博碩士論文加值系統

近年來，由於網際網路的普及，數位影像的使用率大幅提昇，帶動數位相機的使用風潮，但是，原本就提供許多功能的數位相機，為了讓使用者在不同場景(scene)下，都能拍出曝光正確的好照片，都會在數位相機上提供不同的場景模式(scene mode) ，例如風景、海灘…等，供使用者選擇，這讓相機在使用上更為複雜且不方便。如果有單一模式能用於拍攝不同的場景，即能解決使用者需時常切換場景模式的不便。
本篇論文提出了預先分割感興趣區域的場景分類系統，稱為PSROI，它可以在相機執行對焦(S1)的同時，將想要拍攝區域的場景進行分類，並在拍照(S2)後，給予相對應的參數設定值，例如光圈、曝光補償值…等。除此之外，本系統還可整合數位相機對焦系統對焦後的結果到場景分類系統中，依照不同的對焦結果，我們可以動態給予場景分類系統不同的權重(weight)，我們稱此權重為對焦權重(focus weight)，使得場景分類出來的結果能更符合使用者所看到的景像(user vision)。在場景分類系統中，我們預設可分類的場景為人像、風景及沙灘/雪景三種。為了更快速達到場景分類的目的，我們減少影像運算區域、以及應用簡單跟較少運算量的演算法來建構我們的系統。實驗結果證明我們提出的系統架構能有效地將一張影像在0.2秒內正確地分到所屬的類別。

With the popularity of internet in recent years, the usage of digital image is growing dramatically, which raises the trend of using digital cameras. In order to allow users taking good photos with correct exposure in difference scenes, the digital camera provides many scene modes such as scenery, beach…etc for user choosing. However, many scene modes complicate the function of digital cameras and users always feel inconvenient to switch the modes again and again. If a single mode can apply in different scenes, it would solve this inconvenience.
The thesis proposes Pre-Segmented Region Of Interest Classification Scene System, called PSROI, which is able to classify the taking scenes in the time of digital camera processing focus (S1) and give the parameter such as aperture, exposure compensation…etc after taking photos (S2). Besides, it integrates the Focus system. Following different focus result, the different weight is given in the classification scene system, called Focus weight. Focus weight makes the result of classification scene more suitable for user vision. In the classification scene system, three scenes are set, portrait, scenery, and beach/snow. In order to meet the goal of getting the result of classification more quickly, the operation region of image shrinks and simple and less computation is applied to build the system. The result of experiment proves the proposed system is capable of classifying effectively the scenes into the right categories within 0.2 seconds.

Abstract in Chinese i
Abstract in English ii
Acknowledgements in Chinese iii
Table of Contents iv
List of Figures v
List of Tables vi
Chapter 1 Introduction 1
1.1 Scene Classification in Digital Camera 1
1.2 Motivation and Contribution 2
1.3 Overview of the Proposed Organization 3
Chapter 2 Review of Related Works 4
2.1 Features Extraction 4
2.1.1 Color Based Features 4
2.1.2 Texture Based Features 9
2.2 Semantic Features 14
2.3 Scene Classification Systems 15
2.4 Classifiers 18
2.4.1 Support Vector Machines 19
2.4.2 Fuzzy Rule-Based System 20
Chapter 3 Pre-Segmented ROI Scene Classification System 23
3.1 System Overview 24
3.2 Training System 27
3.3 Image Features Extraction 29
3.3.1 Color Features 29
3.3.2 Texture Features 31
3.4 Semantic Feature Extraction 33
3.5 Scene Classification 36
3.6 Integrate Focus Weight to Classification System 37
Chapter 4 Experiments and Discussion 39
4.1 Image database 39
4.2 Horizontal Image classification result 41
4.3 Vertical image classification result 44
4.4 Compare with Other Approach 47
4.5 Discussion 48
Chapter 5 Conclusions 50
References 52

[1] S. Antani, R. Kasturi, and R. Jain, “A survey on the use of pattern recognition methods for abstraction, indexing and retrieval of images and video,” Pattern Recognition, vol. 35, issue 4, pp. 945-965, April 2002.
[2] J. Luo and A. Savakis, “Indoor vs outdoor classification of consumer photographs using low-level and semantic features,” Proceedings of the 2001 International Conference On Image Processing (ICIP 01), Thessaloniki, Greece, vol. 2, pp. 745-748, Oct. 2001.
[3] L. Lu, K. Toyama and G. D. Hager, “A two level approach for scene recognition,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 20-25, Pp. 688-695, June 2005.
[4] F. Naccari, S. Battiato, A. Bruna, A. Capra, and A. Castorina, “Natural scenes classification for color enhancement,” IEEE Transactions on Consumer Electronics, vol. 51, issue 1, pp. 234-239, Feb. 2005.
[5] N. Serrano, A. Savakis, and J. Luo, “Improved scene classification using efficient low-level features and semantic cues,” Pattern Recognition 37(9), pp.1773-1784, Sep. 2004.
[6] O. Chapelle, P. Haffner, and V. N. Vapnik, “Support vector machines for histogram-based image classification,” IEEE transactions on neural networks, vol. 10, issue 5, pp. 1055-1064, Sep. 1999.
[7] L. Cinque, S. Levialdi, K. A. Olsen, and A. Pellicano, “Color-based image retrieval using spatial-chromatic histograms,” IEEE International Conference on Multimedia Computing Systems, Florence, Italy, vol. 2, issue 5, pp. 969-973, 1999.
[8] A. Vailaya, A. Jain, and H. J. Zhang, “On image classification: city vs. landscape,” Proceedings of the 1998 IEEE Workshop on Content-Based Access of Image and Video Libraries, Santa Barbara, CA, USA, pp. 3-8, June 1998.
[9] B. S. Manjunath and W. Y. Ma, “Texture features for browsing and retrieval of image data,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(8), pp. 837-842, Aug. 1996.
[10] M. Turtinen and M. Pietikaine, “Visual training and classification of textured scene images,” the 3rd International Workshop on Texture Analysis and Synthesis (Texture 2003), Nice, France, pp. 101-106. Oct. 2003.
[11] L. W. Renninger and J. Malik, “When is scene identification just texture recognition?” Vision Research, 44, pp. 2301- 2311, June 2004.
[12] S. Arivazhagan and L. Ganesan, “Texture classification using wavelet transform,” Pattern recognition letters, vol. 24, pp. 1513-1521, 2003.
[13] J. Luo and A. E. Savakis, “Two-stage texture segmentation using complementary features,” Proceedings of the 2000 International Conference on Image Processing, Vancouver, BC, vol. 3, pp. 564-567, Sept. 2000.
[14] K. M. Rajpoot, and N. M Rajpoot, “Wavelets and support vector machines for texture classification,” Proceedings of 8th International Multitopic Conference, pp. 328-333, Dec. 2004.
[15] A. Oliva, A. Torralba, A. G. Dugue, and J. Herault, “Global semantic classification of scenes using power spectrum templates,” Challenge of Image Retrieval (CIR99), Electronic Workshops in Computing Series, Sringer-Verlag, Newcastle, 1999.
[16] A. Torralba and A. Oliva, “Semantic organization of scenes using discriminant structural templates,” The Proceedings of the Seventh International Conference on Computer Vision (ICCV99), Kerkyra, pp. 1253-1258, 1999.
[17] S. Foucher, V. Gouaillier, and L. Gagnon, “Global semantic classification of scenes using Ridgelet transform,” Human vision and electronic imaging, Conference No9, San Jose CA , vol. 5292, pp. 402-413, Jan. 2004.
[18] M. Boutell, X. Shen, J. Luo, and C. Brown, “Multi-label semantic scene classification,” Tech. Rep. 813, University of Rochester, Rochester, NY, Sept. 2003.
[19] X. Shen, M. Boutell, J. Luo, and C. Brown, “Multi-label machine learning and its application to semantic scene classification,” International Symposium on Electronic Imaging, San Jose, CA, Jan. 2004.
[20] J. Luo and M. Boutell, “A probabilistic approach to image orientation detection via confidence-based integration of low-level and semantic cues,” 4th International Workshop on Multimedia Data and Document Engineering (in conjunction with CVPR2004), Washington, DC, July 2004.
[21] G. H. Hu, J. J. Bu, and C. Chen, “A novel Bayesian framework for indoor-outdoor image classification,” IEEE International Conference on Machine Learning and Cybernetics, vol. 5, pp. 3028-3032, Nov. 2003.
[22] M. Szummer and R.W. Picard, “Indoor-outdoor image classification,” Proceedings of IEEE International Workshop on Content-based Access of Image and Video Databases, Bombay, India, pp. 42-51, 1998.
[23] B. C. Ko, H. S. Lee, and H. Byun, “Image retrieval using flexible image subblocks,” Proceedings of the 2000 ACM symposium on Applied computing 2000, pp.574-578, March 2000.
[24] B. L. Saux and G. Amato, “Image classifiers for scene analysis,” International Conference on Computer Vision and Graphics 2004.
[25] J. Luo, M. Boutell, R. T. Gray, and C. Brown, “Image transform bootstrapping and its applications to semantic scene classification,” IEEE Transactions on Systems, Man, and Cybernetics, Part B, vol. 35, No. 3, June 2005.
[26] A. Vailaya, M. Figueiredo, A. Jain, and H. J. Zhang, “A Bayesian framework for semantic classification of outdoor vacation images,” Proc. SPIE Storage Retrieval Image Video Databases VII, San Jose, CA, vol. 3656, pp. 415-426, Jan. 1999.
[27] J. Luo, A. E. Savakis, and A. Singhal, “A Bayesian network-based framework for semantic image understanding,” Pattern Recognition, vol. 38, No. 6, pp. 919-934, June 2005.
[28] J. Luo, A. E. Aavakis, S. P. Etz, and A. Singhal, “On the application of Bayes networks to semantic understanding of consumer photographs,” Proceedings of the 2000 International Conference on Image Processing, Vancouver, BC, vol. 3, pp. 512-515, Sept. 2000.
[29] Y. Tsin, R. T. Collins, V. Ramesh, and T. Kanade, “Bayesian color constancy for outdoor object recognition,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2001), vol. 1, pp. I-1132-I-1139, Dec. 2001.
[30] M. Boutell and J. Luo, “Bayesian fusion of camera metadata cues in semantic scene classification,” IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, vol. 2, pp. 623-630, June 2004.
[31] M. Boutell and J. Luo, “Photo classification by integrating image content and camera metadata,” Proceedings of the 17th International Conference on Pattern Recognition, vol. 4, pp. 901-904, Aug. 2004.
[32] A. Singhal and J. Luo, “Probabilistic spatial context models for scene content understanding,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. I-235-I-241, June 2003.
[33] T. Ehtiati and J. J. Clark, “A strongly coupled architecture for contextual object and scene identification,” Proceedings of the 17th International Conference on Pattern Recognition (ICPR 2004), vol. 3, pp. 69-72, Aug. 2004.
[34] S. Kumar, A. C. Loui, and M. Hebert, “Probabilistic classification of image regions using an observation-constrained generative approach,” ECCV Workshop on Generative Models based Vision (GMBV), pp. 91-99, 2002.
[35] M. Boutell and J. Luo, “A generalized temporal context model for semantic scene classification,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW’04), June 2004.
[36] M. Boutell and J. Luo, “Incorporating temporal context with content for classifying image collections,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW’04), vol. 2, pp. 947-950, June 2004.
[37] A. Bosch, X. Munoz, A. Olivr, and R. Marti, “Object and scene classification: what does a supervised approach provide us?” Proceeding of the 18th International Conference on Pattern Recognition (ICPR 2006), vol. 1, pp. 773-777, Aug. 2006.
[38] A. Vailaya, M. A. T. Figueiredo, A. K. Jain, and H. J. Zhang, “Image classification for content-based indexing,” IEEE Transactions on Image Processing, vol. 10, issue 1, pp. 117-130, Jan. 2001.
[39] J. Vogel and B. Schiele, “Semantic modeling of natural scenes for content-based image retrieval,” International Journal of Computer Vision, 2004.
[40] A. Torralba and A. Oliva, “Statistics of natural image categories,” Network, vol. 14, pp. 391-412, 2003.
[41] J. Luo and S. P. Etz, “A physical model-based approach to detecting sky in photographic images,” IEEE Transactions of Image Processing, vol. 11, issue 3, pp. 201-212, Mar. 2002.
[42] P. Lipson, E. Grimson, and P. Sinha, “Configuration based scene classification and image indexing,” Proceedings of the 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1007-1013, Jun. 1997.
[43] B. L. Saux and G. Amato, “Image recognition for digital libraries,” Proceedings of the 6th ACM SIGMM international workshop on Multimedia information retrieval, pp. 91-98, 2004.
[44] O. V. Kaick and G. Mori, “Automatic classification of outdoor images by region matching,” The 3rd Canadian Conference on Computer and Robot Vision, June 2006.
[45] C. Nello and S. T. John, An introduction to Support Vector Machines and other kernel-based learning methods, Cambridge, New York, 2000.
[46] H. Ishibuchi and T. Yamamoto, “Rule weight specification in fuzzy rule-based classification systems,” IEEE Transactions on Fuzzy Systems, vol. 13, no. 4, pp. 428-435, Aug. 2005.
[47] J. Luo, R. T. Gray, and H. C. Lee, “Towards physics-based segmentation of photographic color images,” Proceedings of the 1997 International Conference on Image Processing, vol. 3, pp. 58-61, Oct. 1997.
[48] C. C. Chang and C. J. Lin, “LIBSVM: a library for support vector machines,” 2001, Software available at: http://www.csie.ntu.edu.tw.
[49] C. W. Hsu and C. J. Lin, “A comparison of methods for multi-class support vector machines,” IEEE Transactions on Neural Networks, vol. 13(2), pp. 415-425, 2002.