臺灣博碩士論文加值系統

本論文即在提出一自動化的交通標誌辨識系統，以提供充分的交通標誌相關訊息給駕駛者，讓駕駛者可以正確判斷道路環境。本文主要著重於複雜背景之交通標誌偵測與辨識。
所提方法主要分為二個階段:交通標誌的偵測及辨識。這二個階段的設計原理分別是基於色彩資訊、區塊資訊和幾何資訊。在偵測階段，首先將色彩空間RGB轉為HSV，以偵測出具有標誌特定色彩的區塊。在辨識階段，以幾何特徵、投影特徵交集法及Moments之特徵值做比對。

The purpose of this thesis is to propose an automatic road sign recognition system so that car drivers can have sufficient information to make a correct decision. This thesis emphasize on detection and recognition in complicated background.
The method consists of two phases: road sign detection and recognition. The two phases are based on color information,region information and geometric information. In the detection stage,the RGB color space converted into HSV color space to detect those regions with specific colors of road signs.In the recognition stage,the characteristic of the Shape,Moment and projection intersection method are using to recognize.

中文摘要………………………………………………………………Ⅰ
英文摘要………………………………………………………………Ⅱ
致謝……………………………………………………………………Ⅲ
目錄……………………………………………………………………Ⅳ
圖表索引………………………………………………………………Ⅵ
第一章 序論…………………………………………………………1
1.1 研究動機與目的…………………………………………………1
1.2 相關文獻探討……………………………………………………2
1.3 研究方法之限制條件……………………………………………4
1.4 全文架構…………………………………………………………4
第二章 影像前處理…………………………………………………6
2.1 彩色空間的轉換…………………………………………………6
2.1.1 RGB彩色空間 …………………………………………………6
2.1.2 HSV彩色空間 …………………………………………………6
2.2 形態學……………………………………………………………8
2.2.1 二値化…………………………………………………………8
2.2.2 膨脹與腐蝕……………………………………………………11
2.2.3 開運算與閉運算………………………………………………14
2.2.4 標籤化…………………………………………………………15
2.3 拉普拉斯算子濾波………………………………………………16
2.4 中值濾波…………………………………………………………17
2.5 Moments特徵抽取 ………………………………………………18
第三章 偵測與辨識方法……………………………………………21
3.1 交通標誌偵測……………………………………………………21
3.1.1 顏色判定………………………………………………………21
3.1.2 雜點去除………………………………………………………24
3.1.3 標誌的幾何特性………………………………………………29
3.1.4 前處理…………………………………………………………32
3.2 交通標誌辨識……………………………………………………35
3.2.1 幾何特徵分類…………………………………………………35
3.2.2 投影特徵交集法圖形比對……………………………………37
第四章 實驗結果……………………………………………………53
第五章 結論與未來發展……………………………………………60
參考文獻………………………………………………………………61
附錄A …………………………………………………………………63

[1]內政部警政署之統計資料,"警察機關受(處)理A1類道路交通事故概況",2007.
[2]K. Rangarajan,M. Shah and D. V. Brackle."Optimal corner detector,"Computer Vision,Graphics,and Image Processing, Vol.48,pp.230-245,1989.
[3]R. Janssen,W. Ritter,F. Stein,and S. Ott,"Hybrid approach for traffic sign recognition,"Proceedings of the Intelligent Vehicles 1993 Symposium,pp.390-395,1993.
[4]G. Piccioli,E. D. Michel,P. Parodi,and M. Campani," Robust method for road sign detection and recognition," Image and Vision Computing,Vol.14,pp.209-223,1996.
[5]A. D. L. Escalrea,L. E. Moreno,M. A. Salichs,and J. M. Armingol,"Road traffic sign detection and classification," IEEE Transactions on Industrial Electronics,Vol.44,No.6, pp.848-859,1997.
[6]K. Hirose,T. Askura and Y. Aoyagi,"Real-time recognition of road traffic sign in moving scene image using new image filter,"Proceedings of the 26th Annual Confence of the IEEE Industrial Electronics Society,Vol.3,pp.2207-2212,2000.
[7]S. H. Hsu and C. L. Huang,"Road sign detection and recognition using matching pursuit method,"Image and Vision Computing,Vol.19,pp.119-129,2001.
[8]教育資料館,"道路交通標誌標線號誌設置規則",1998.
[9]N. Otsu,"A threshold selection method from gray-level histogram,"IEEE Trans. Syst.,Man,Cybern,Vol. SMC-8,pp.62-66,1978.
[10]連國珍,"數位影像處理",儒林圖書,2004.
[11]謝瑩亮,"英文文件中之字元特徵擷取與辨識",國立台灣海洋大學電機工程研究所碩士學位論文,2006.