本論文目的在於建立一套以Multiple-Instance learning (MIL)為基礎之影像搜尋系統，著重於影像資訊在空間關係之比對，以衡量影像在空間關係上之相似程度，提供使用者能夠適當利用感興趣之查詢影像搜尋出符合需求之資料庫影像。而在單張查尋影像可能包含許多空間關係，常常無法代表使用者真正有興趣之空間關係資訊。藉由輸入多張與目標影像正、負相關之查詢影像，透由Multiple-Instance Learning 法則，自動找出與正相關影像相似特徵及與負相關影像不相似部份，動態搜尋使得搜尋特徵更加明確。以MIL後之空間關係特徵作為檢索標準，即可符合使用者期望，以求影像搜尋之正確性及多樣性。
而空間關係相似度量測對應於Interval Neighbor Group (ING)上相關空間關係節點間最短距離，若距離愈短，則具有較高相似程度；反之距離愈遠，則具有較低相似程度。一旦任兩張影像間兩兩相對應物件所組成pairwise空間關係相似值都被決定出後，空間關係相似性量測結構將可以給予兩張影像一個整體之相似程度。因此影像資料庫中所有影像皆可與查詢影像作相似度計算，並由大至小將相似程度作排名，方便使用者搜尋出相似程度較高之影像。因此，影像空間關係特徵間一個可靠之相似性量測系統即可被發展出來，藉由單張查詢影像或多張查詢影像機制，給予適當相似程度。
為了證明提出之相似性衡量法則具有可靠性以及正確性，給予查詢影像藉由兩種測試方法與影像資料庫中影像作相似程度比對，分別為提出之RSS-ING機制與2D Be-string相似度量測方法。並透過single-instance與multiple-instance learning來比對搜尋結果之有效性。搜尋效能上利用相似度分類精細度曲線，執行時間以及記憶體存取大小等參數，來驗證所提出MIL空間關係相似性量測結構可作為將來影像搜尋上之工具。

The objective of the present work is to employ a multiple-instance learning image retrieval system by incorporating a spatial similarity measure. Multiple-Instance learning is a way of modeling ambiguity in supervised learning given multiple examples. From a small collection of positive and negative example images, semantically relevant concepts can be derived automatically and employed to retrieve images from an image database. The degree of similarity between two spatial relations is linked to the distance between the associated nodes in an Interval Neighbor Group (ING). The shorter the distance, the higher degree of similarity, while a longer one, a lower degree of similarity. Once all the pairwise similarity values are derived, an ensemble similarity measure will then integrate these pairwise similarity assessments and give an overall similarity value between two images. Therefore, images in a database can be quantitatively ranked according to the degree of ensemble similarity with the query image. Similarity retrieval method evaluates the ensemble similarity based on the spatial relations and common objects present in the maximum common subimage between the query and a database image are considered. Therefore, reliable spatial relation features extracted from the image, combined with a multiple-instance learning paradigm to derive relevant concepts, can produce desirable retrieval results that better match user’s expectation.
In order to demonstrate the feasibility of the proposed approach, two sets of test for querying an image database are performed, namely, the proposed RSS-ING scheme v.s. 2D Be-string similarity method, and single-instance vs. multiple-instance learning. The performance in terms of similarity curves, execution time and memory space requirement show favorably for the proposed multiple-instance spatial similarity-based approach.

第一章 影像資料庫搜尋之相關研究..................................1
1.1 以文字為基礎之影像搜尋..........................................1
1.2 以影像內容為基礎之影像搜尋..................................2
1.3 以空間關係為特徵之搜尋..........................................4
1.3.1　空間關係表示法..............................................4
1.3.2 空間關係為基礎之影像相似度量測...............16
1.3.3 影像空間關係旋轉及鏡射探討.......................23
1.4 結合多張影像之搜尋機制........................................25
1.5 研究概述....................................................................26
第二章 相似性量測研究步驟............................................29
2.1 空間關係相似性比對...............................................29
2.1.1 對於一對一空間關係相似性量測....................29
2.1.2 對於多對一空間關係相似性量測....................34
2.1.3 對於多對多空間關係相似性量測....................37
2.2 結合多張正負相關影像之搜尋機制.......................42
2.2.1 Multiple-Instance Learning...........................42
2.2.2 Diverse Density Algorithm............................43
2.2.3 計算 Pγ ( t | Bi).................................................45
2.2.4 Diverse Density應用於ING...........................46
第三章 空間關係相鄰圖位元序列編碼...........................49
3.1 影像轉換之空間關係探討.......................................49
3.2 空間關係位元序列編碼...........................................52
3.2.1 定義位元序列編碼...........................................52
3.2.2 由位元序列編碼推導空間關係屬性...............55
第四章 實驗結果與討論...................................................66
第五章 結論與未來展望...................................................80
參考文獻............................................................................81

[1] F. Cannavale, A. Casanova, M. Fraschini, and V. Savona, “Content Image Retrieval Based on Topological Information,” J. Vis. Lang. Comput, Vol. 15, No. 5, pp. 347-359, Oct. 2004.
[2] Y. Chen and J. Z. Wang, “A Region-Based Fuzzy feature Matching Approach to Content-Based Image Retrieval,” IEEE Trans. Pattern Anal. Mach. Intell., Vol. 24, No. 9, pp. 1252-1267, Sept. 2002.
[3] R. Billen and S. Zlatanova, “3D Spatial Relationships Model: A Useful Concept for 3D Cadastre?,” Comput. Environ. Urban Sys., Vol. 27, No. 4, pp. 411-425, 2003.
[4] G. Qiu, “Indexing Chromatic and Achromatic Patterns for Content-based Colour Image Retrieval,” Pattern Recogni., Vol. 35, No. 8, pp. 1675-1686, 2002.
[5] S. Berretti, A. Del Bimbo, and E. Vicario, “Spatial Arrangement of Color in Retrieval by Visual Similarity,” Pattern Recogni., Vol. 35, No. 8, pp. 1661-1674, 2002.
[6] Y. Chi and K. H. Leung, “ALSBIR： A local-structure-based image retrieval,” Pattern Recogni., Vol. 40, pp. 244-261, 2007.
[7] W. C. Lin, Y. C. Chang and H. H. Chen, “Integrating textual and visual information for cross-language image retrieval: A trans-media dictionary approach,” Inf. Process. Manage., Vol. 43, No. 2, pp. 488-502, 2007.
[8] P. W. Huang, and S. K. Dai, “Image Retrieval by Texture Similarity,” Pattern Recogni., Vol. 36, pp. 665-679, 2003.
[9 ]W. Niblack, R. Barber, W. Equitz, M. Flickner, E. Glasman, D. Petkovic, P. Yanker, C. Faloutsos and G. Taubin, “The qbic project: Quering images by content using color, texture, and shape,” in Proc. SPIE conf., Vol. 2, No. 3, pp. 173-187, 1993.
[10] A. Pentland, R. W. Picard and S. Sclaroff, “Photobook: Content-based manipulation of image databases,” Int. J. Comput. Vis., Vol. 18, No. 3, pp. 233-254, 1996.
[11] J. Vleugels and R. C. Veltkamp, “Efficient image retrieval through vantage objects,” Pattern Recogni., Vol. 35, No. 1, pp. 69-80, 2002.
[12] X. Liu, S. Shekhar and S. Chawla, “Object-based Directional Query Processing in Spatial Databases,” IEEE Trans. Knowl. Data Eng, Vol. 15, No. 2, 2003.
[13] P. Punitha and D. S. Guru, “An Invariant Scheme for Exact Match Retrieval of Symbolic Images : Triangular Spatial Relationship Based Approach,” Pattern Recogni., Vol. 26, pp. 893-907, 2005.
[14] A. J. T. Lee and H. P. Chiu and P. Yu, “3D C-string: a new spatio-temporal knowledge representation for video database systems,” Pattern Recogni., Vol. 11, No. 35, pp. 2521-2537, 2002.
[15] S. K. Chang, Q. Y. Shi, and C. W. Yan, “Iconic Indexing by 2D Strings,” IEEE Trans. Pattern Anal. Mach. Intell., Vol. 9, No. 3, pp. 413-428, 1987.
[16 ]C. C. Chang, “Spatial Machine Retrieval of Symbolic Pictures,” J. Info. Sci. Eng., Vol. 7, No. 3, pp. 405-422, 1991.
[17] D. Chaudhuri and A. Samal, “A simple method for fitting of bounding rectangle to closed regions,” Pattern Recogni., Vol. 40, No. 7, pp. 1981-1989, 2007.
[18] S. K. Chang, E. Jungert, and Y. Li, “Representation and Retrieval of Symbolic Pictures Using Generalized 2D Strings,” Technical Report, University of Pittsburg, 1988.
[19] S. Y. Lee and F. J. Hsu, “Spatial Reasoning and Similarity Retrieval of Images Using 2D C-String Knowledge Representation,” Pattern Recogni., Vol. 25, No. 3, pp. 305-318, 1992.
[20] P. W. Huang and Y. R. Jean, “Using 2D C+-string as spatial knowledge representation for image database systems,” Pattern Recogni., Vol. 27, No. 9, pp. 1249-1257, 1994.
[21] A. J. T. Lee and H. P. Chiu, “2D Z-string: A New Spatial Knowledge Representation for Image Databases,” Pattern Recogni., Vol. 24, No. 16, pp. 3015-3026, Dec. 2003.
[22] M. Nabil, J. Shepherd and A. H. H. Ngu, “Picture Similarity Retrieval Using 2D Projection Interval Representation,” IEEE Trans. Knowl. Data Eng, Vol. 8, No. 4, pp. 533-539, 1996.
[23] C. Freska, “Temporal Reasoning Based on Semi-Intervals,” Artif. Intell., Vol. 54, No. 1, pp. 199-227, 1992.
[24] S. M. Hsieh and C. C. Hsu, “Graph-based representation for similarity retrieval of symbolic images,” IEEE Trans. Knowl. Data Eng, Vol. 65, No. 3, pp. 401-418, 2008.
[25] P. Punitha and D. S. Guru, “An effective and efficient exact match retrieval scheme for symbolic image database systems based on spatial reasoning: A logarithmic search time approach,” IEEE Trans. Knowl. Data Eng, Vol. 18, No. 10, pp. 1368-1381, 2006.
[26] P. Punitha, D. S. Guru and P. Nagabhushan, “Archival and retrieval of symbolic images: An invariant scheme based on triangular spatial relationship” Pattern Recogni. Lett., Vol. 24, pp. 2397-2408, 2003.
[27] Y. H. Wang, “Image indexing and similarity retrieval based on spatial relationship model,” Inf. Sci.: Int. J., Vol. 154, No. 1-2, pp. 39-58, 2003.
[28] T. K. Shin, C. S. Wang, A. Y. Chang and C. H. Kao, “Indexing and retrieval scheme of the image database based on color and spatial relations,” IEEE Int. Conf. ICME, 2000.
[29] El-Kwae and M. R. Kabuka, “A robust framework for content-based retrieval by spatial similarity in image databases,” ACM Trans. on Info. Sys., Vol. 17, No. 2, pp. 174-198, 1999.
[30] S. Y. Sung and T. Hu, “Iconic pictorial retrieval using multiple attributes and spatial relationships,” Knowl. Based Sys., Vol. 19, No. 8, pp. 687-695, December 2006.
[31] S. M. Hsieh, C. C. Hsu, “Retrieval of images by spatial and objects similarities,” Inf. Process. Manage., Vol. 44, No. 3, pp. 1214-1233, 2008.
[32] M. Kazhdan, T. Funkhouser, and S. Rusinkiewicz, “Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptions,” in Proc. ACM SIGRAPH, pp. 156-164, 2003.
[33] W. H. Yeh, and Y. I. Chang, “An Efficient Iconic Indexing Strategy for Image Rotation and Reflection in Image Databases,” J. Sys. Software, Vol. 81, No. 7, pp. 1184-1195, 2008.
[34] D. R. Dooly, S. A. Goldman, S. S. Kwek, “Real-valued multiple-instance learning with queries,” J. Comput. Sys. Sci., Vol. 72, No. 1, pp. 1-15, 2006.
[35] O. Maron and A. L. Ratan, “Multiple-instance learning for natural scene classification,” in Proc. 15th Int'l Conf. on Machine Learning, 1998.
[36] G. Petraglia, M. Sebillo, M. Tucci, and G. Tortora, “Virtual Images for Similarity Retrieval in Image Databases” IEEE Trans. Knowl. Data Eng, Vol. 13, No. 6, pp. 951-967, 2001.