臺灣博碩士論文加值系統

在這個進步的都市中，人們對於車輛的需求日益增多情況下，許多已開發的國家都致力於運用目前先進的電子、通訊、資訊以及管理技術來發展「智慧型運輸系統 」 （Intelligent Transportation System, ITS） ，並解決人們生活上的問題，使人們的生活更便利，而「車牌辨識系統」（License Plate Recognition）則是 ITS 裡的其中一項重要應用，其中「車牌定位」是一個重要的環節，定位的成果會影響後續字元分割的正確性和字元辨識的辨識率。
本論文提出即時車牌定位模型（Real-time License Plate Position Model, RLPM）達到車牌定位的方法，在訓練階段採用Haar-like特徵的擷取，透過Cascade AdaBoost機器學習演算法產生出一個聯級式的分類器；在定位階段先由分類器進行分類，選出含有車牌特徵的區域，在篩選確認階段使用垂直投影的方法篩選出車牌區域，最後定位出車牌位置。
本實驗結果顯示，本論文提出的即時車牌定位模型（RLPM），在定位測試下，端正的車牌影像定位成功率達93.5%，整體定位成功率達80.6%，由此可知，本論文提出的RLPM在定位車牌位置有不錯的效果。

In this progressive city, there is an increasing demand for vehicles, many developed countries are committed to use the advanced electronics, communications, information and management technologies to develop the Intelligent Transportation System. （ITS） to solve people's problems in life, and to make people's lives more convenient. "License Plate Recognition" is one of the most important applications in ITS. "Car license plate position" is an important part. The result of position recognition will affect the accuracy of subsequent characters segmentation and the identification rate of characters recognition.
This paper proposes a real-time License Plate Position Model （RLPM） to achieve license plate position. Using the Haar-like features in the training section, and a cascaded classifier is generated by the Cascade AdaBoost machine learning algorithm. In the position section, the classifier classifies license plate and which selects the area of containing the license plate features. The license plate area is screened which using the vertical projection method during the screening confirmation section. Finally, to locate the license plate location.
The experimental results show that the Real-time License Plate Position Model （RLPM） proposed in this paper, under the positioning test, has a correct success rate of license plate image positioning are 93.5% and an overall positioning success rate are 80.6%. It can be seen that the RLPM proposed in this paper has a good effect in locating the license plate position.

摘要iii
Abstractv
致謝vi
目錄vii
圖目錄viii
表目錄ix
符號x
第一章 緒論12
1.1研究背景與動機12
1.2研究目的12
1.3論文架構13
第二章 文獻探討14
2.1特徵擷取14
2.2機器學習演算法（Machine Learning）16
2.3二值化─Otsu法20
第三章 研究方法22
3.1 Haar-like特徵22
3.2 Cascade-AdaBoost學習演算法24
3.3垂直投影28
第四章 實驗結果與討論33
4.1環境設置35
4.2實驗結果35
4.3實驗討論42
第五章 結論與未來發展44
參考文獻46

[1]Bai, H., Zhu, J., and Liu, C., "A Fast License Plate Extraction Method on Complex Background," in Intelligent Transportation Systems, IEEE Proceedings. vol 2, 12-15Page（s）:985- 987, Oct., 2003.
[2]Bai, H., and Liu, C., "A hybrid license plate extraction method based on edge statistics and morphology," in Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on vol. 2, pp. 831-834, Aug., 2004.
[3]Kong, J., Liu, X., Lu, Y., and Zhou, X., "A novel license plate localization method based on textural feature analysis," in Signal Processing and Information Technology, 2005. Proceedings of the Fifth IEEE International Symposium on pp. 275-279, Dec., 2005.
[4]Khan, S.M., Atamturktur, S., Chowdhury, M., and Rahman, M., "Integration of structural health monitoring and intelligent transportation systems for bridge condition assessment: current status and future direction," IEEE Transactions on Intelligent Transportation Systems, vol. 17, no. 8, pp. 2107-2122, 2016.
[5]Wu, H.T., and Horng, G.J., "Establishing an Intelligent Transportation System With a Network Security Mechanism in an Internet of Vehicle Environment," IEEE Access, vol. 5, pp. 19239-19247, 2017.
[6]Suryanarayana, P.V., Mitra, S.K., Banerjee, A., and Roy, A.K., "A morphology based approach for car license plate extraction," in 2005 Annual IEEE India Conference - Indicon, Dec., 2005.
[7]P. Dubey, "Heuristic approach for license plate detection," in IEEE Conference on Advanced Video and Signal Based Surveillance, 2005., Sep., 2005.
[8]Zhang, Y., and Zhang, C., "A new algorithm for character segmentation of license plate," in IEEE IV2003 Intelligent Vehicles Symposium. Proceedings （Cat. No.03TH8683）, Jun., 2003.
[9]Khan, M.A., Sharif, M., Javed, M.Y., Akram, T., Yasmin, M., and Saba, T., "License number plate recognition system using entropy-based features selection approach with SVM.," IET Image Processing, vol. 12, no. 2, pp. 200-209, 2017.
[10]Youting, Z., Zhi, Y., and Xiying, L., "Evaluation methodology for license plate recognition systems and experimental results," IET Intelligent Transport Systems, vol. 12, no. 5, pp. 375-385, 2018.
[11]Wu, B., and Nevatia, R., "Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors," in Tenth IEEE International Conference on Computer Vision （ICCV'05）, Oct., 2005.
[12]Wu, C., Duan, L., Miao, J., Fang, F., and Wang, X., "Detection of front-view vehicle with occlusions using adaboost," in 2009 International Conference on Information Engineering and Computer Science, Dec., 2009.
[13]Zhang, L., Chu, R., Xiang, S., Liao, S., and Li, S.Z., "Face detection based on multi-block lbp representation," in International Conference on Biometrics, Berlin, Heidelberg, Aug., 2007.
[14]Han, S., Han, Y., & Hahn, H., "Vehicle detection method using Haar-like feature on real time system," in World Academy of Science, Engineering and Technology, 2009.
[15]A. Cuthbertson, "CES 2016: Ford promises to launch 13 electric vehicles by 2020 plus drone-to-vehicle technology," Jan. 2016. [Online].
[16]Ban, Y., Kim, S.K., Kim, S., Toh, K.A., and Lee, S., "Face detection based on skin color likelihood," Pattern Recognition, vol. 47, no. 4, pp. 1573-1585, 2014.
[17]Yang, G., and Huang, T.S., "Human face detection in a complex background.," Pattern recognition, vol. 27, no. 1, pp. 53-63, 1994.
[18]Li, C., Gao, G., Liu, Z., Yu, M., and Huang, D., "Fabric defect detection based on biological vision modeling," IEEE Access, vol. 3, no. 4, 2018.
[19]Yang, J., and Waibel, A., "A real-time face tracker," Dec., 1996.
[20]Yow, K.C., and Cipolla, R., "Feature-based human face detection," Image and vision computing, vol. 15, no. 9, pp. 713-735, 1997.
[21]Leung, T. K., Burl, M. C., and Perona, P., “Finding faces in cluttered scenes using random labeled graph matching,” 1995.
[22]Dai, Y., and Nakano, Y., "Face-texture model based on SGLD and its application in face detection in a color scene," Pattern recognition, vol. 29, no. 6, pp. 1007-1017, 1996.
[23]Ye, L., Cao, Z., and Xiao, Y, "DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features," IEEE Transactions on Geoscience and Remote Sensing, vol. 55, no. 10, pp. 5729-5740, 2017.
[24]Huang, L.L., Shimizu, A., Hagihara, Y., and Kobatake, H., "Face detection from cluttered images using a polynomial neural network," Neuro computing, vol. 51, pp. 197-211, 2003.
[25]Huang, L.L., Shimizu, A., Hagihara, Y., and Kobatake, H., “Gradient feature extraction for classification-based face detection,” Pattern Recognition, pp. 2501-2511, 2003.
[26]Yang, H., Zheng, S., Lu, J., and Yin, Z., "Polygon-invariant generalized Hough transform for high-speed vision-based positioning," IEEE Transactions on Automation Science and Engineering, vol. 13, no. 3, pp. 1367-1384.
[27]Craw, I., Tock, D., and Bennett, A., "Finding face features," in European Conference on Computer Vision — ECCV'92, Berlin, Heidelberg., May.1992.
[28]Lanitis, A., Taylor, C.J., and Cootes, T.F., "Automatic face identification system using flexible appearance models," Image and vision computing, vol. 13, no. 5, pp. 393-401, 1995.
[29]Wu, Y., Chen, H., Zhao, X., & Zhai, Y., "A vision-based recognition method for transformer based on adaboost and multi-template matching," in In: Cyber Technology in Automation, Control, and Intelligent Systems （CYBER）, 2015 IEEE International Conference on. , June, 2015.
[30]Zhu, Q., Yeh, M.C., Cheng, K.T., and Avidan, S., "Fast human detection using a cascade of histograms of oriented gradients," in Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on vol. 2, pp. 1491-1498, 2006.
[31]Papageorgiou, C.P., Oren, M., and Poggio, T. , "A general framework for object detection," in In Computer vision, 1998. sixth international conference on pp. 555-562, Jan., 1998.
[32]Viola, P., and Jones, M, "Rapid object detection using a boosted cascade of simple features," in In Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on vol. 1, pp. I-511 - I-518, 2001.
[33]Chang, C.Y., & Fu, S.Y., "Image classification using a module RBF neural network," in Innovative Computing, Information and Control, 2006. ICICIC'06. First International Conference on vol. 2, pp. 270-273, Aug., 2006.
[34]Cheon, M., Lee, W., Yoon, C., and Park, M., "Vision-based vehicle detection system with consideration of the detecting location," IEEE transactions on intelligent transportation systems, vol. 13, no. 3, pp. 1243 - 1252, 2012.
[35]Berz, E.L., Tesch, D.A., and Hessel, F.P., "Machine-learning-based system for multi-sensor 3D localisation of stationary objects," IET Cyber-Physical Systems: Theory & Applications., vol. 3, no. 2, 2018.
[36]Doyle, S., Feldman, M., Tomaszewski, J., and Madabhushi, A., "A boosted Bayesian multiresolution classifier for prostate cancer detection from digitized needle biopsies," IEEE transactions on biomedical engineering, vol. 59, no. 5, pp. 1205-1218, 2012.
[37]V. Vapnik, The nature of statistical learning theory, Springer science and business media, 2013.
[38]Freund, Y., and Schapire, R.E., "A decision-theoretic generalization of on-line learning and an application to boosting," Journal of computer and system sciences, vol. 55, no. 1, pp. 119-139, 1997.
[39]Lienhart, R., Kuranov, A., and Pisarevsky, V, "Empirical analysis of detection cascades of boosted classifiers for rapid object detection," in Joint Pattern Recognition Symposium （pp. 297-304）, Berlin, Heidelberg, Sep.,2003.
[40]Sezgin, M., and Sankur, B, "Survey over image thresholding techniques and quantitative performance evaluation," Journal of Electronic imaging, vol. 13, no. 1, pp. 146-166, 2004.
[41]Khambampati, A.K., Liu, D., Konki, S.K., and Kim, K.Y., "An Automatic Detection of the ROI Using Otsu Thresholding in Nonlinear Difference EIT Imaging," IEEE Sensors Journal, vol. 18, no. 12, pp. 5133-5142, June 2018.
[42]N. Otsu, "A threshold selection method from gray-level histograms," IEEE transactions on systems, man, and cybernetics, 9（1）, 62-66., vol. 9, no. 1, pp. 62-66, 1979.