臺灣博碩士論文加值系統

對影像內容的檢索系統Content-based image retrieval (CBIR)已經被廣泛的應用在相關領域，但是在實務運用上還有背景處理的問題需要解決，例如商業攝影的圖像資料中，不乏使用陪襯物品去營造整體商品視覺感受；再以數位典藏系統為例，所採集台灣花卉群譜的生態影像，其圖片通常伴隨與目標植物特徵無關之背景景物，也將造成背景影像干擾影像圖片訓練的結果，導致檢索結果的準確率降低。所以我們提出基於人類視覺注意模式(Visual Attention Model)自動化擷取感興趣的影像區域(Region of Interest)，做為訓練資料集的主體物件，提高檢索準確率。
數位相機普及和網路的生活化，造成社群網路上數位影像成倍數的成長。面對高資料量、高計算量及型態變化速度極快的數位影像，我們使用在資料採礦(Data mining)中不需要事先定義訓練樣本的非監督式學習方法，將數位影像做有效的分群(Clustering)，因為類神經網路對於高資料量的訓練樣本有較好的表現，我們用自組織映射圖(Self-Organizing Map, SOM)演算法來對數位影像做學習訓練，經過實驗獲得不錯的成果。

Content-based images retrieval (CBIR) has been widely used in many application fields. Yet, in commercial photography, ornaments and décor are often used to better the vision of the product as a whole. The images of the digital archive system for Taiwan flower anthography group are usually accompanied by other background objects that have nothing to do with the target plant. The background noise will decrease the precision rate of image retrieval.
Therefore, we propose a method based on Visual Attention Model to extract image area of interest as training datasets, thus improving the retrieval precision rate. The number of digital images is growing rapidly in social networks due to the popularity of the Internet and digital cameras. To deal with the large amount of image data and computation cost, we choose the Self-Organizing Map (SOM) as our unsupervised learning algorithm. As an efficient Artificial Neural Network approach, SOM is useful for visualizing low-dimensional views of high-dimensional data. Our experiments show good performance results.

致謝 ii
摘 要 iii
Abstract iv
目 錄 v
圖目錄 viii
表目錄 x
第一章 緒論 1
1.1研究背景與動機 1
1.2研究目的 3
1.3研究限制 4
1.4解決方案 4
第二章 文獻研究與回顧 7
2.1顏色空間模型(Color Space Model) 7
2.1.1 HSV模型： 7
2.2特徵值(Feature Extraction ) 8
2.2.1顏色特徵(Color Feature) 8
2.2.1尺度不變特徵點轉換(SIFT) 9
2.3 調降維度(Dimensionality Reduction) 10
2.4 視覺注意模式(Visual Attention Model) 11
2.4.1 影像金字塔 (Image Pyramid) 14
2.4.2 特徵圖 (Feature Map) 16
2.5影像分割(Image Segmentation) 20
2.6分類器(Classifier) 21
2.6.1自組織映射圖網路(Self-Organizing Map) 23
第三章 研究方法與步驟 24
3.1系統概述 24
3.2 研究方法 28
第四章 實驗結果與評估 35
4.1實驗環境 35
4.2評估方式 36
4.3實驗結果 37
第五章 結論與未來研究 47
5.1優點 47
5.2缺點 48
5.3結論 49
5.4未來研究 50
參考文獻 51
作者簡介 55

[1]H.-C. Yang and C.-H. Lee, “Image semantics discovery from web pages for semantic-based image retrieval using self-organizing maps,” Expert Systems with Applications, Vol. 34, No. 1, pp. 266-279, 2008.
[2]K. Trojacanec, I. Dimitrovski, and S. Loskovska, “Content based image retrieval in medical applications: an improvement of the two-level architecture,” Proceedings of the EUROCON 2009, EUROCON ''09. IEEE, pp. 118-121, 2009.
[3]G. T. Ozyer and F. Y. Vural, “A Content-Based Image Retrieval system using Visual Attention,” Proceedings of the Signal Processing and Communications Applications Conference (SIU), 2010 IEEE 18th, pp. 399-402, 2010.
[4]B. V. Jyothi and K. Eswaran, “Comparative Study of Neural Networks for Image Retrieval,” Proceedings of the Intelligent Systems, Modelling and Simulation (ISMS), 2010 International Conference on, pp. 199-203, 2010.
[5]S. Feng, D. Xu, and X. Yang, “Attention-driven salient edge(s) and region(s) extraction with application to CBIR,” Signal Process., Vol. 90, No. 1, pp. 1-15, 2010.
[6]E. Z. Barcelos, E. L. Flores, C. A. Z. Barcelos, S. F. Silva, and M. A. Batista, “A Multi-Dimensional Similarity Modeling and Relevance Feedback Approach for Content-Based Image Retrieval,” Proceedings of the Systems, Signals and Image Processing, 2009. IWSSIP 2009. 16th International Conference on, pp. 1-5, 2009.
[7]辜雅婷，以特徵離散性為基礎的影像內容檢索相關回饋機制，台南大學數位學習科技學系碩士論文，2009。
[8]王战辉，基于内容的服装图像检索技术研究，西安理工大學碩士學位論文，2010。
[9]卢兴敬，基于内容的服装图像检索研究 ，華中科技大學碩士學位論文，2008。
[10]龚思思，基于形状特征的服装图像检索技术应用研究，北方工業大學碩士學位論文，2009。
[11]張慧，基於內容的服裝圖像檢索，華南理工大學碩士學位論文，2010。
[12]L. Itti, C. Koch, and E. Niebur, “A model of saliency-based visual attention for rapid scene analysis,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol. 20, No. 11, pp. 1254-1259, 1998.
[13]L. Itti and C. Koch, “A saliency-based search mechanism for overt and covert shifts of visual attention,” Vision Research, Vol. 40, No. 10-12, pp. 1489-1506, 2000.
[14]T. Kohonen, “The self-organizing map,” Proceedings of the IEEE, Vol. 78, No. 9, pp. 1464-1480, 1990.
[15]D. G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” Int. J. Comput. Vision, Vol. 60, No. 2, pp. 91-110, 2004.
[16]D. G. Lowe, “Object recognition from local scale-invariant features,” Proceedings of the Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on, pp. 1150-1157, 1999.
[17]L. Wei, X. Weidong, L. Lihua, and L. Guoliang, “Two new bag generators with multi-instance learning for image retrieval,” Proceedings of the Industrial Electronics and Applications, 2008. ICIEA 2008. 3rd IEEE Conference on, pp. 255-259, 2008.
[18]Z. Li and L. Itti, “Saliency and Gist Features for Target Detection in Satellite Images,” Image Processing, IEEE Transactions on, Vol. PP, No. 99, pp. 1-1, 2011.
[19]Y. Lei, X. Gui, and Z. Shi, “Feature Description and Image Retrieval Based on Visual Attention Model,” Journal of Multimedia, Vol. 6, No. 1, pp. 56-65, 2011.
[20]S. Hae Jong and P. Milanfar, “Visual saliency for automatic target detection, boundary detection, and image quality assessment,” Proceedings of the Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on, pp. 5578-5581, 2010.
[21]S. Feng, C. Lang, and D. Xu, “Beyond tag relevance: integrating visual attention model and multi-instance learning for tag saliency ranking,” Proceedings of the ACM International Conference on Image and Video Retrieval, pp. 288-295, 2010.
[22]R. Achanta, S. Hemami, and F. Estrada, “Frequency-tuned salient region detection,” Proceedings of the Computer Vision and Pattern Recognition, pp. 1597-1604, 2009.
[23]C. K. J. Harel, and P. Perona, “Graph-Based Visual Saliency,” Advances in Neural Information Processing Systems, pp. 545–552, 2007.
[24]L. Elazary and L. Itti, “Interesting objects are visually salient,” Journal of Vision, Vol. 8, No. 3, pp. 3.1-15, 2008.
[25]N. Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Transactions on Systems, Man and Cybernetics, Vol. 9, No. 1, pp. 62-66, 1979.
[26]M. E. Nilsback and A. Zisserman, “Automated Flower Classification over a Large Number of Classes,” Proceedings of the Computer Vision, Graphics & Image Processing, pp. 722-729, 2008.