跳到主要內容

臺灣博碩士論文加值系統

(44.200.86.95) 您好!臺灣時間:2024/05/28 08:16
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:徐建業
研究生(外文):Chien-Yeh Hsu
論文名稱:混合色彩空間以及區域紋理特徵之商標辨識系統
論文名稱(外文):Hybrid Color spatial features and Local texture features for Content-Based Trademark Retrieval
指導教授:范國清范國清引用關係
指導教授(外文):Kuo-Chin Fan
學位類別:碩士
校院名稱:國立中央大學
系所名稱:資訊工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
畢業學年度:97
語文別:中文
論文頁數:72
中文關鍵詞:商標檢索系統
外文關鍵詞:color spatialcbirtrademarkimage retrieval
相關次數:
  • 被引用被引用:5
  • 點閱點閱:538
  • 評分評分:
  • 下載下載:150
  • 收藏至我的研究室書目清單書目收藏:1
隨著商標資料庫的增加,容易遇到商標相似度過高,或是仿冒的問題。但是龐大的商標資料庫如果只依賴人工來進行分類以及相似商標之搜尋、比對的話,勢必會耗費大量的人力資源及時間成本。相似商標之準確度也可能因為作業流程而下降。
本篇論文提出一種混合色彩空間特徵,以及區域紋理特徵兩種方法的商標辨識系統。首先將圖片進行前處理,去除不必要的白色邊緣部份,只留下系統所需要的商標部份,並且對它進行放大縮小、平移這兩種正規化。接著將圖片等分成數個大小相同的區域,計算各個區域中之色彩平均值,此為第一項特徵。第二項特徵是將商標圖片進行二值化的運算,再利用區域二維特徵來表示。
在實驗中,使用者會輸入一張查詢影像,由上述兩項特徵來對所有資料庫中的商標圖案進行相似度的比對。而因為相似度的判定是形狀相似大於色彩相似,所以本方法會給予區域二維特徵較高的權重。
經過多種方法實驗比較之下,本篇論文提出之商標辨識系統在準確度上的表現較其他單一種檢索方法更為優異,因此結果顯示本論文實驗方法具可行性。
With the increasing amount of trademarks in trademark database, one will suffer the problem in retrieving similar or counterfeit trademarks. It is very time-consuming to classify, verify and retrieve the huge amount of trademarks by human intervention. Moreover, the accuracy of classification will decline with time due to human factor.
In this thesis, we propose a trademark retrieval system by hybridizing color-spatial features and the local texture features. Firstly, preprocessing of trademark image is performed to remove unnecessary part of the white edge and retain the region of interest that we need. Normalization with scaling and shifting is also accomplished in this step. Then, divide the image into a number of regions and calculate the color mean value of each region, which is the first feature extracted of the retrieval system. The second feature is to binarize the trademark image and use two-dimensional features as local features to represent the image.
In retrieval, the user will input a query image and execute the similarity measurement by utilizing the proposed features with all the stored trademarks in the database. Since the discrimination power of shape is higher then color by experimentation, the two-dimensional characteristic region be assigned higher weight in similarity measurement.
By conducting various experiments, the accuracy of the proposed trademark retrieval system outperforms other retrieve methods. It demonstrates the feasibility and efficiency of the proposed system in trademark retrieval.
口試委員會審定書 #
摘要 1
ABSTRACT 2
目錄 3
附圖目錄 5
附表目錄 8
第1章 簡介 10
1.1 研究動機 13
1.2 相關研究 16
1.3 系統流程 19
1.4 論文架構 21
第2章 背景知識 22
第3章 商標影像前處理 26
3.1 影像尺寸及平移之正規化 26
3.2 色彩空間轉換 – 灰階 29
3.3 色彩空間轉換 – 二值化 30
第4章 特徵擷取與比對 32
4.1 色彩空間特徵 32
4.2 區域紋理特徵 34
4.3 Zernike 矩量 (Zernike Moment Measurement) 37
4.4 影像距離比對 41
4.5 相似度排序 41
第5章 實驗結果與分析 43
5.1 實驗影像(Ground Truth images) 43
5.2 實驗結果 48
5.2.1 使用Precision比較系統正確率 53
5.2.2 使用 Recall rate 比較系統正確率 58
第6章 結論與未來工作 64
6.1 結論 64
6.2 未來工作 64
參考文獻 66
[1]Y. S. Kim, W. Y. Kim, ” Content-based trademark retrieval system using a visually salient feature” Image and Vision Computing Volume 16, Issues 12-13,August 1998, Pages 931-939.
[2]Xiao jun Qi , Yu tao Han, “A novel fusion approach to content-based image retrieval” Pattern Recognition Volume 38, Issue 12, December 2005, Pages 2449-2465.
[3]Cai-kou Chen, Qiang-qiang Sun and Jing-yu Yang,” Binary Trademark Image Retrieval Using Region Orientation Information Entropy” Computational Intelligence and Security Workshops, December 2007, Pages 295-298.
[4]John P. Eakins, Jago M. Boardman and Margaret E. Graham,” Similarity Retrieval of Trademark Images” International Conference on Image Analysis and Processing, Volume 5, Issue 2, April 1998, Pages 53 – 63.
[5]R. Pradeep Kumar, P. Nagabhushan, “An Approach Based on Regression Line Features for Low Complexity Content Based Image Retrieval”, International Conference on ICCTA, March 2007, Pages 600-604.
[6]Sanjoy Kumar Saha, Amit Kumar Das and Bhabatosh Chanda, “CBIR using Perception based Texture and Colour Measures”, 17th International Conference on Pattern Recognition, Volume 2, 2004, Pages 985 – 988.
[7]Day-Fann Shen, Li Jin, Hsuan T Chang and Hsien Huang P. Wu, ” Trademark Retrieval Based On Block Feature Index Code”, IEEE International Conference on Image Processing, Volume 3, September 2005, Pages 177-80.
[8]Jim Z. C. Lai, Yi-Ching Liaw and Julie Liu, “A fast VQ codebook generation algorithm using codeword displacement”, Pattern Recognition Volume 41, Issue 1, January 2008, Pages 315-319.
[9]Pasi Fränti, Timo Kaukoranta, Day-Fann Shen and Kuo-Shu Chang, “Fast and Memory Efficient Implementation of the Exact PNN”, IEEE Transactions on Image Processing, Volume 9, May 2000, Pages 773-777.
[10]Yoseph Linde, Andres Buzo and Robert M. Gray, “An Algorithm for Vector Quantizer Design”, IEEE Transactions on Communications Volume 28, January 1980, Pages 84-95.
[11]Ming-Kuei Hu, “Visual Pattern Recognition by Moment Invariants”, IRE Transactions on Information Theory, Volume 8, February 1962, Issue 2, Pages 179-187.
[12]Whoi-Yul Kim, Yong-Sung Kim, “A region-based shape descriptor using Zernike moments”, Signal Processing: Image Communication, Volume 16, September 2000, Pages 95-102.
[13]Chia-HungWei, Yue Li, Wing-YinChaub and Chang-TsunLi, “Trademark image retrieval using synthetic features for describing global shape and interior structure”, Pattern Recognition, Volume 42, Issue 3, March 2009, Pages 386-394.
[14]Jun Zhang, Jinglu Hu, “Image Segmentation Based on 2D Otsu Method with Histogram Analysis”, International Conference on Computer Science and Software Engineering, Volume 6, December 2008, Pages 105-108.
[15]Zhang Lei, Lin Fuzong and Zhang Bo, “A CBIR method based on color-spatial feature”, Tencon 99. Proceedings of the IEEE Region 10 Conference, Volume 1, September 1999, Pages 166-169.
[16]A. Suruliandi, K. Ramar, “Local Texture Patterns –A Univariate Texture Model for Classification of Images”, Advanced Computing and Communications, December 2008, Pages 32-39.
[17]Alireza Khotanzad, Yaw Hua Hong, “Invariant Image Recognition by Zernike Moments”, Pattern Recognition Letters, Volume 26, Issue 6, May 2005, Pages 747-753.
[18]Chong-Yaw Wee, Raveendran Paramesran, “On the computational aspects of Zernike moments”, Image and Vision Computing, Volume 25 Issue 6 , June 2007, Pages 967-980.
[19]J´erˆome Revaud, Guillaume Lavou´e and Atilla Baskurt, “Optimal similarity and rotation angle retrieval using Zernike moments”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 31, Issue 4, April 2009, Pages 627-636.
[20]Sun-Kyoo Hwang, Whoi-Yul Kim, “A novel approach to the fast computation of Zernike moments”, Pattern Recognition, Volume 35, Issue 12, December 2002, Pages 2905-2911.
[21]Mustafa Ozden, Ediz Polat, “A color image segmentation approach for content-based image retrieval”, Pattern Recognition, Volume 40, Issue 4, April 2007, Pages 1318-1325.
[22]Zhiling Hong, Qingshan Jiang, “Hybrid Content-based Trademark Retrieval using Region and Contour Features”, Advanced Information Networking and Applications - Workshops, March 2008, Pages 1163-1168.
[23]http://en.wikipedia.org/wiki/Content-based_image_retrieval
[24]http://www.npm.gov.tw/
[25]http://cobweb.ecn.purdue.edu/RVL/Research/CBIR/index.html
[26]http://tineye.com/
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊