在現代，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,因此如何使用現有的監視系統資源獲取即時資訊變成一個很重要的議題。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。車牌辨認系統是以從監視畫面中偵測車牌為目的的智慧監控系統。一般監控系統的偵測對象是以汽車車牌為主，但本
論文試著把偵測對象延伸至機車車牌。
如果要偵測機車車牌內容，使用現有的演算法將會面臨一些困難。本論文修改了現有的影像二值化演算法，以克服常發生在機車車牌中的陰影影響。亦改進了原本的字元切割演算法，減少貼在機車車牌上的貼紙影響。在車牌字元偵測方面，我們由一種通用字元切割演算法的靈感，提出一種新的比對特徵。比起目前大家常用的比對特徵，它有節省儲存樣本空間和比對時間較少的優勢。

In recent year, surveillance system is employed widely. The surveillance system is usually applied to monitor specify target for special purpose. Therefore, how to use existing surveillance system to gather information in real time becomes an important issue. Intelligence surveillance system helps us to get interested information from the screen shoot. License plate recognition system is an intelligence surveillance system which detects the license plate from images. In usual, the targets which system deals with are the vehicle license plates. In this thesis, we try to extend the targets to scooter license plates.

Using existing algorithms to detect scooter license plates would face some difficulties. We modify existing binarization algorithm to overcome shade effect which often occurs on scooter license plates. The original character segmentation algorithm is also improved to
reduce the effect caused by the sticks on license plates. In character recognition, we provide a new comparison feature which is improved from a popular character segmentation algorithm. Comparing with the feature which people often use recently, it costs smaller storage space and less computing time.

[1] Giancarlo Alessandretti, Alberto Broggi. Vehicle and guard rail detection using radar
and vision data fusion. IEEE Transactions on Intelligent Transportation Systems,
8(1):95-105, March 2007
[2] 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.
[3] Christos Nikolaos E. Anagnostopoulos, Ioannis E. Anagnostopoulos, Vassili Loumos,
and Eleftherios Kayafas. A license plate-recognition algorithm for intelligent
transportation system applications. IEEE Transactions on Intelligent Transportation
Systems, 7(3):377-392, September 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] Gisu Heo, Minwoo Kim, Insook Jung, Duk-Ryong Lee, Il-Seok Oh. Extraction of car
license plate regions using line grouping and edge density methods. 2007. ISITC 2007.
International Symposium on Information Technology Convergence, 37-42, November
2007.
[6] Song Huansheng and Wang Guoqiang. The high performance car license plate
recognition system and its core techniques. 2005. IEEE International Conference on
Vehicular Electronics and Safety, 42-45, October 2005.
[7] Yo-Ping Huang, Shi-Yong Lai and Wei-Po Chuang. A template-based model for license
54
plate recognition., 2004 IEEE International Conference on Networking, Sensing and
Control,Networking, Sensing and Control, 2:737-742, 2004
[8] 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.
[9] C. L. Lai, J. C. Yang, and Y. H. Chen. A real time video processing based surveillance
system for early fire and flood detection. 2007 IEEE Instrumentation and Measurement
Technology Conference Proceedings, 1-6, May 2007.
[10] Khan, Nabeel Younus, Imran, Ali Shariq and Ali, Naveed Distance and Color Invariant
Automatic License Plate Recognition System. ICET 2007. International Conference
on Emerging Technologies, 232-237, Nov. 2007
[11] TANG Shuang-tong and LI Wen-ju. Number and letter character recognition of vehicle
license plate based on edge Hausdorff distance. Proceedings of the Sixth International
Conference on Parallel and Distributed Computing, Applications and Technologies,
850-852, 2005.
[12] Luo-Wei Tsai and Jun-Wei Hsieh. Vehicle detection using normalized color and edge
map. IEEE Transactions on Image Processing, 16(3): 850-864, March 2007.
[13] Shen-Zheng Wang and His-Jian Lee. Detection and recognition of license plate
characters with different appearances. 2003. Proceedings. 2003 IEEE Intelligent
Transportation Systems, 2:979-984, October 2003.
[14] Shen-Zheng Wang. A sascade framework for a real-rime statistical late recognition
system. IEEE Transactions on Information Forensics and Security, 2(2):267-282, June
2007
[15] Feng Yang, Zheng Ma, and Mei Xie. A robust character segmentation approach for
license plate. 2007. ICCCAS 2007. International Communications, Circuits and
Systems, 679-683, July 2007.
[16] 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.
[17] Yungang Zhang and Changshui Zhang. A new algorithm for character segmentation of
license plate. 2003. Proceedings. IEEE Intelligent Vehicles Symposium, 106-109, June
2003.