簡易檢索 / 詳目顯示

回結果列表
研究生： 王詩瑀
Wang, Shih-Yu
論文名稱： 利用投影量法對貨櫃號碼做偵測與切割
A Method of Container Codes Detection and Segmentation by Using Improved Projection Algorithm
指導教授： 戴顯權
Tai, Shen-Chuan
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 電腦與通信工程研究所
Institute of Computer & Communication Engineering
論文出版年： 2010
畢業學年度： 98
語文別： 英文
論文頁數： 55
中文關鍵詞： 貨櫃識別碼 、投影量法 、字元偵測 、字元切割
外文關鍵詞： container codes, projection algorithm, codes detection, character segmentation
相關次數： 點閱：94  下載：3 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 在現在的日常生活中，監視系統的使用越來愈普遍。監視系統通常為了特定目的而觀察特定對象，智慧監測系統可以從監視畫面裡即時擷取重要資訊給我們。除了應用在生活環境的安全監控與人、車流量資料統計之外，也廣泛的應用在管理方面。因此如何善用現有的監視系統資源以減少人力資源，並同時提高管理效率成為一個重要的議題。然而現今的監控系統的偵測對象是以車輛車牌辨認系統為大宗，本論文試著把偵測對象延伸至貨櫃。

    如果要使用車牌偵測的方法來偵測貨櫃辨別標記，現有的演算法將會面臨一些困難。本論文提出了適用於貨櫃的字元區域擷取方法，亦改進了原本的字元切割演算法，使其亦可應用在不固定排數的字元偵測，並減少貨櫃上垂直的槓桿以及貨櫃識別碼周圍其它標記的影響。

    In recent year, surveillance system is widely used in our daily life. The surveillance system is usually applied to monitor specify target for special purpose. Intelligence surveillance system can helps us to get interested information from the monitor screen. In addition to applied to security monitor in our living environment and people or traffic flow statistics, it also widely used in management. Therefore, how to use existing surveillance system to improve the accuracy rate while reducing the human resources is an important issue. Most of the current surveillance systems focus on license plate detection, this thesis try to extend the detect object to the containers.

    The existing license plate detection algorithm will face some difficulties using on container codes detection. This thesis presents a character region extraction method for containers. And also improved projection method to reduce the effect caused by bars or marks on container and make it can be used to detect irregular rows of characters.

    Contents ............................................... vi List of Tables ....................................... viii List of Figures ........................................ ix Chapter1 Introduction ................................... 1 1-1 Introduction of Container Identify System ........... 1 1-2 Organization of the Thesis .......................... 2 Chapter2 Background and Related Work .................... 3 2-1 License Plate Detection ............................. 3 2-1.1 Edge Detection .................................... 7 2-1.2 Edge point ratio ................................. 10 2-2 Color extraction of license plate .................. 12 2-2.1 HSI color space .................................. 12 2-3 Characters Segmentation ............................ 13 Chapter3 Proposed Container Codes Detection and Segmentation with Improved Projection Algorithm .........16 3-1 The Identification System of Intermodal Containers 16 3-1.1 Comparison of container codes and license plate .. 19 3-2 Interesting Region Extraction ...................... 23 3-2.1 Edge Detection ................................... 23 3-2.2 Grouping ......................................... 24 3-3 Delaminating ....................................... 27 3-4 Detection and Segmentation ......................... 30 3-4.1 Horizontal Projection ............................ 30 3-4.2 Vertical Projection .............................. 33 3-5 Refinement ......................................... 36 Chapter4 Simulation Results .............................37 4-1 Result of interesting region extraction ............ 37 4-2 Result of delaminating ............................. 41 4-3 Result of character segmentation ................... 44 4-3.1 Horizontal projection ............................ 44 4-3.2 Vertical projection .............................. 47 Chapter5 Conclusions and Future Work ....................51 Reference ...............................................53

    [1] Mello C.A.B. and Costa D.C. A Complete System for Vehicle License Plate Recognition. IWSSIP 2009 16th. Systems, International Conference on Signals and Image Processing, 1-4, June 2009.

    [2] Ya-Wen Chiang, Yo-Chen Wang, Yan-Yau Jiang, and Yuan-Hsiang Chang. A Bill-Detection System Based on Color and Texture Analyses. http://cvl.ice.cycu.edu.tw/publications/Chiang2006.pdf , June 2006.

    [3] Xiaojun Chil, Junyu Dong, Aihua Liu, and Huiyu Zhou. A simple method for Chinese license plate recognition based on support vector machine. 2006 International Conference on Communications, Circuits and Systems Proceedings, 3:2141-2145, June 2006.

    [4] Jing-Ming Guo and Yun-Fu Liu. License plate localization and character segmentation with feedback self-learning and hybrid-binarization techniques. IEEE Transactions on Vehicular Technology, 57(3):1417-1424, May 2008.

    [5] Xiaodan Jia, Xinnian Wang, Wenju Li, and Haijiao Wang. A novel algorithm for character segmentation of degraded license plate based on prior knowledge. 2007 IEEE International Conference on Automation and Logistics, 249-253, August 2007.

    [6] Deb, K., Heechul Lim, and Kang-Hyun Jo. Vehicle license plate extraction based on color and geometrical features. ISIE 2009. IEEE International Symposium on Industrial Electronics, 1650 - 1655, July 2009.

    [7] Miao Ligang, Wang Fengwen, and Wang Han. Automatic license plate detection based on edge density and color model. CCDC '09. Control and Decision Conference, 3718 - 3721, June 2009.

    [8] Youjie Qiu, Min Sun, and Wenling Zhou. License Plate Extraction Based on Vertical Edge Detection and Mathematical Morphology. CiSE 2009. International Conference on Computational Intelligence and Software Engineering, 1-5, Dec 2009. Yungang Zhang and Changshui Zhang. A new algorithm for character segmentation of license plate. 2003. Proceedings. IEEE Intelligent Vehicles Symposium, 106-109, June 2003.

    [9] Jun Ren Su and Zheng Ma. Car License Plate Location Based on the Density and Projection. CINC '09. International Conference on Computational Intelligence and Natural Computing, (1): 409 – 412, June 2009.

    [10] Hsiao-Yun Tseng, Ching-Hao Lai, and Shyr-Shen Yu. An effective license-plate detection method for overexposure and complex vehicle images. 2008 International Conference on Convergence and Hybrid Information Technology, 176 – 181, Sep 2008.

    [11] Wanniarachchi, W., Sonnadara, D., and Jayananda, M.K.. License Plate Identification Based on Image Processing Techniques. ICIIS 2007. International Conference on Industrial and Information Systems, 373 - 378 , Aug 2007.

    [12] Jianxia Wang, Guilong Gao, and Huili Yang. Research and implementation of license plate location based on histogram division method. ICEMI '09. 9th. International Conference on Electronic Measurement & Instruments, (1):230-233, Aug 2009.

    [13] Xianchao Zhang, Xinyue Liu, and He Jiang. A hybrid approach to license plate segmentation under complex conditions. The 3rd International Conference on Natural Computation, 68-73, August 2007.

    [14] Fabao Yan, Xianhe Shao, Gun Li, Zhiyin Sun, and Zhongjun Yang. Edge Detection of Tank Level IR Imaging Based on the Auto-Adaptive Double-Threshold Canny Operator. IITA '08. Intelligent Information Technology Application, (3): 366 – 370, Dec 2008.

    [15] Cheng Zhangfan and Chen Rongbao. License plate location method based on modified HSI model of color image. ICEMI '09. 9th. International Conference on Electronic Measurement & Instruments, (4):197 - 201, Aug 2009.

    [16] Gaussian Smoothing, http://homepages.inf.ed.ac.uk/rbf/HIPR2/gsmooth.htm, 2003.

    [17] Canny edge detector, http://en.wikipedia.org/wiki/Canny_edge_detection, May 2010.

    [18] HSL and HSV, http://en.wikipedia.org/wiki/HSL_and_HSV , June 2010.

    下載圖示 校內：2011-07-19公開
    校外：2015-07-19公開
    QR CODE