近年來我國經濟的快速發展，產品推陳出新，商品與日俱增，連帶的商標（Trademark）亦有增無減，再加上近年來著作及智慧財產權觀念的建立，如何設計一個商標，不至於去侵犯到現有已註冊商標也變成越來越重要。
對於影像資料庫的搜尋，傳統上是以人工對影像加以描述，再對這些文字描述加以搜尋，這是相當費時且不正確的方法。故現今研究多朝向以影像的內容特徵進行影像檢索，這種基於影像內容的檢索方法，稱為「內容基礎的影像檢索」（content-based image retrieval, CBIR）。
由於商標相似最重要的判別依據是人眼，且根據人眼觀點和法規可知其相似又以外型最重要。故本論文提出一使用者自訂特徵加權的回饋式人機介面，結合Zernike矩量和本論文提出的影像緊密度係數、影像包覆性係數為影像特徵做相似檢索。

The need of finding a way to design a company trademark, without the worry of possible infringement on the intellectual property rights, has become exceedingly important as the economy and the accompanying intellectual property concerns advanced greatly in recent years.
Traditionally, registered trademarks are stored in image databases and are categorized and retrieved by descriptions and keywords given by human workers. This is extremely time-consuming and considered by many as inappropriate. In this work we focus on image feature and content related techniques, or content-based image retrieval (CBIR) methods.
Nevertheless, we still need human inputs since by law the most crucial basis for discerning the similarity or difference of two trademarks has to rely on human’s naked eye. Therefore in this work we created a program which incorporates an man-machine interface allowing users to input various weighting factors each emphasizing a specific feature or shape of the trademark. The Zernike moments, and some new image compactness indices are used in the computations for image comparisons.

謝 誌 I
目 錄 II
圖目錄 V
表目錄 VIII
摘 要 IX
Abstract X
第一章 緒論 - 1 -
1.1 文獻探討 - 3 -
1.2 研究動機與目的 - 6 -
1.3 論文架構 - 8 -
第二章 知識背景 - 9 -
2.1 商標概述 - 9 -
2.2 色彩空間 - 15 -
2.2.1 RGB色彩模型 - 15 -
2.2.2 灰階 - 16 -
2.3 矩量（Moments） - 17 -
2.3.1 Hu 不變矩量（Invariant Moments） - 17 -
2.3.2 Zernike矩量 - 19 -
2.4 最小封閉圓（Smallest enclosing circle） - 32 -
2.5 凸面殼（Convex Hull） - 35 -
2.6 影像緊密度（Image Compactness Indices） - 37 -
2.6.1 包覆輪廓 - 37 -
2.6.2 影像緊密度係數 - 39 -
2.6.3 影像包覆性係數 - 39 -
第三章 實驗方法 - 41 -
3.1 實驗流程 - 41 -
3.2 影像前處理 - 42 -
3.2.1 色彩轉換 - 42 -
3.2.2 最小封閉圓 - 44 -
3.2.3 緊密輪廓 - 44 -
3.2.4 正規化 - 44 -
3.3 特徵擷取 - 45 -
3.3.1 Zernike矩量 - 45 -
3.3.2 影像緊密度 - 48 -
3.4 特徵加權 - 49 -
3.5 特徵距離與相似度計算 - 50 -
第四章 實驗結果與分析 - 52 -
4.1 實驗資料 - 52 -
4.2 實驗前處理 - 55 -
4.3 實驗結果 - 57 -
4.3.1 相似商標檢索 - 57 -
4.3.2 實際變化影像檢索 - 65 -
4.3.3 變形影像檢索 - 70 -
4.4 討論分析 - 75 -
第五章 結論 - 80 -
參考文獻 - 82 -
附 錄 - 85 -

[1] H. Freeman, “On the encoding of arbitrary geometric configurations”, IRE Transaction on Electronic Computing, Vol. 10, pp. 260-268, 1961.
[2] G. Cortelazzo, G. A. Mian, G. Vezzi, P. Zamperoni, “Trademark shapes description by string-matching techniques”, Pattern Recognition, Vol. 27, pp. 1005-1018, 1994.
[3] H. L. Peng, S. Y. Chen, “Trademark shape recognition using closed contours”, Pattern Recognition Letters, Vol. 18, pp. 791-803, 1997.
[4] P. Y. Yin, C. C. Yeh, “Content-based retrieval from trademark databases”, Pattern Recognition Letters, Vol. 23, pp. 113-126, 2002.
[5] M. K. Hu, “Visual pattern recognition by moment invariants”, IRE Transactions on Information Theory, pp. 179-187, 1962.
[6] J. L. Shih, L. H. Chen, “A new system for trademark segmentation and retrieval”, Image and Vision Computing, Vol. 19, pp. 1011-1018, 2001.
[7] G. Ciocca, R. Schettini, “Content-based similarity retrieval of trademarks using relevance feedback”, Pattern Recognition, Vol. 34, pp. 1639-1655, 2001.
[8] Y. S. Kim, W. Y. Kim, “Content-based trademark retrieval system a visually salient feature”, Image and Vision Computing, Vol. 16, pp. 931-939, 1998.
[9] S. D. Lin, S. C. Shie, W. S. Chen, B. Y. Shu, X. L. Yang, Y. L. Su, “Trademark image retrieval by distance-angle pair-wise histogram”, International Journal of Imaging Systems and Technology, Vol. 15, pp. 103-113, 2005.
[10] H. K. Kim, J. D. Kim, D. G. Sim, D. I. Oh, “A modified Zernike moment shape descriptor invariant to translation, rotation and scale for similarity-based image eetrieval”, IEEE International Conference on Multimedia and Expo, Vol. 1, pp.307-310, 2000.
[11] N. K. Kamila, S. Mahapatra, S. Nanda, ”Invariance image analysis using modified Zernike moment”, Pattern Recognition Letters, Vol. 26, pp.747-753, 2005.
[12] 康炎村，商標註