(3.236.222.124) 您好!臺灣時間:2021/05/19 10:40
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:::

我願授權國圖
: 
twitterline
研究生:楊仁華
研究生(外文):Jen-Hua Yang
論文名稱:可攜式車牌辨識系統之演算法研究
論文名稱(外文):A Study of Algorithms for Handheld License Plate Recognition System
指導教授:呂紹偉詹景裕詹景裕引用關係
指導教授(外文):Show-Wei LeuGene-Eu Jan
學位類別:碩士
校院名稱:國立臺灣海洋大學
系所名稱:電機工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:中文
論文頁數:88
中文關鍵詞:可攜式裝置車牌辨識影像處理
外文關鍵詞:image processinglicense plate recognitionhandheld device
相關次數:
  • 被引用被引用:10
  • 點閱點閱:446
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:1
車牌辨識系統經過多年發展,目前已有不少商業應用,但主要是以定置型電腦為計算平台,如停車場出入管理等相關應用。本論文提出一種適於可攜式影像擷取裝置之車牌辨識演算法,使得車牌辨識的實現更有彈性。此演算法在硬體資源有所限制的環境下,可達到八成以上的辨識率及單一車牌約兩秒的執行時間。
本論文所提出之車牌辨識演算法實作於定點式數位訊號處理器上,包含車牌定位、字元切割及字元辨識等三個階段。車牌定位步驟利用影像輪廓及亮度特徵來進行定位,並利用影像縮圖提升計算速度;字元切割步驟則先以複合式車牌水平度校正方法進行處理,提升切割及後續步驟的正確率;字元辨識步驟使用階層式單層類神經網路來進行辨識,藉此解決相似字型辨識問題。
本研究在DSP開發板上實現本論文所提出之LPR演算法。經過實驗,本論文平均辨識率為87.2%。上述結果是基於539張影像所組成的樣本空間,其中每張影像均包含一個或一個以上的車牌,採用不同的拍攝角度,並且在不同的天氣及亮度條件之下。根據上述初步的實驗結果可以得知,本論文所提出之LPR演算法具有相當的潛力,可將一般常見附照相功能的可攜式裝置提升為具有車牌辨識能力的設備,並具有合理的辨識率。
Automatic license plate recognition has attracted many researchers’ attention in recent years, and their efforts have resulted in many installed business applications. However, most existing installations are non-moving, such as automatic parking control and payment systems. In order to provide flexibility for implementation, this thesis develops a set of algorithms suitable for realizing license plate recognition (LPR) capability on handheld mobile devices. The general design goal is for a handheld device with limited hardware resources to be able to read a license plate from a picture containing a single license plate image within two seconds and with 80% or higher rate of successful recognition.

The proposed LPR algorithm consists of three major steps, namely, license plate location, character segmentation, and character recognition. Plate location is achieved mainly by extracting image outlines of probable areas. For pictures of acceptable quality, two-dimensionally reduced images are used to save processing time. To separate the characters with higher accuracy, the character segmentation step applies the techniques of hybrid rotation correction. Finally, an one-layer artificial neural network is deployed for character recognition.

We have implemented the proposed LPR algorithm on a DSP-based development board. The experimental results show that, the total average rate of successful recognition is 87.2%. This is based on a sample space of 539 pictures including the ones containing more than a single license plate, taken with various shooting angles and under a range of weather and light conditions. This preliminary result also shows that our proposed LPR algorithm has the potential to give today’s many picture-taking mobile devices the ability to recognize license plates with reasonably high recognition rate.
致謝…………………………………………………………………………I
摘要………………………………………………………………………..II
Abstract………………………………………………………………….IV
目錄……………………………………………………………………….VI
圖目錄…………………………………………………………………….IX
表目錄………………………………………………………………… ..XII
第一章 緒論……………………………………………………………...1
1.1 研究動機……………………………………………………….....1
1.2 相關研究概述………………………………………………….....2
1.3 論文架構……………………………………………………………..3
第二章 車牌辨識系統……..………………….…………………………4
2.1 系統概要…………………………………………………………....4
2.2基本影像操作方式與資料結構…………………………………….5
2.2.1座標記錄串列與影像儲存串列………………………………..6
2.2.2連接物件編碼方式之一………………………………………10
2.2.3連接物件編碼方式之二………………………………………13
2.3 系統流程與簡介…………………………………………………..15
第三章 車牌定位……………………………….……………….....19
3.1 車牌特徵擷取……………………………………………………..19
3.1.1影像輪廓擷取…………………………………………………19
3.1.2輪廓密集度判定………………………………………………22
3.1.3灰階影像二值化………………………………………………24
3.2車牌影像定位第一階段…………………………………………...25
3.2.1縮圖定位………………………………………………………26
3.2.2縮圖定位詳細步驟……………………………………………27
3.3車牌影像定位第二階段…………………………………………...31
3.3.1第二階段定位詳細步驟………………………………………31
3.3.2其他背景雜訊消除運算………………………………………35
第四章 車牌字元切割與辨識………………………………………….37
4.1 字元連接物件擷取………………………………………………..37
4.1.1字元連接物件擷取方式及特徵………………………………37
4.1.2字元連接物件相關操作應用…………………………………40
4.2車牌傾斜度校正…………………………………………………...43
4.2.1傾斜度校正運算………………………………………………43
4.2.2複合式傾斜度校正機制………………………………………45
4.3 字元切割步驟……………………………………………………..48
4.4 字元辨識步驟……………………………………………………..53
4.4.1字元辨識步驟流程簡介………………………………………53
4.4.2相似字元調整…………………………………………………56
第五章 實驗與效能分析……………………………………………….59
5.1 實驗環境……………………………………………………......59
5.1.1實驗設備………………………………………………………59
5.1.2測試樣本環境…………………………………………………60
5.2 實驗結果……….………………………………………………….62
5.2.1車牌定位步驟結果……………………………………………62
5.2.2字元切割步驟結果……………………………………………64
5.2.3字元辨識步驟結果……………………………………………67
5.3 整體執行效能分析………………………………………………69
第六章 結論與未來發展…………………………………….......72
參考文獻………………………………………………………………….73
[1] 官宗?,利用數位訊號處理器實現車牌字元辨識系統,國立台灣大學電機工程學研究所碩士學位論文,1999。
[2] 王中山,使用小波轉換於車牌偵測,國立中山大學機械與機電工程學系碩士論文,2003。
[3] 林家緯,以統計數據為基礎的車牌影像處理與辨識方法,國立中山大學機械與機電工程學系碩士論文,2004。
[4] 呂炎坤,不限環境之車牌定位系統,靜宜大學資訊管理學系碩士論文,2007。
[5] 李志文,嵌入式即時多標的汽機車牌照辨識系統,國立台灣科技大學電子工程系碩士論文,2008。
[6] 八木伸行、林正樹、三谷公二、奧井誠人、吳上立、林宏墩,C語言數位影像處理,全華出版,2005。
[7] C. Arth, F. Limberger, and H. Bischof, “Real-Time License Plate Recognition on an Embedded DSP-Platform,” IEEE Conference on Computer Vision and Pattern Recognition, 2007.
[8] C. Arth, “Visual Surveillance on DSP-Based Embedded Platforms,” Ph.D. dissertation, Graz University of Technology, Institute for Computer Graphics and Vision, 2008.
[9] C. N. E. Anagnostopoulos, I. E. Anagnostopoulos, V. Loumos, and E. Kayafas, “A License Plate-Recognition Algorithm for Intelligent Transportation System Applications,” IEEE Transactions on Intelligent Transportation Systems, Vol. 7, No. 3, September 2006.
[10] D. R. Lee, S. H. Jin, P. C. Thien, and J. W. Jeon, “FPGA Based Connected Component Labeling,” International Conference on Control, Automation and Systems, pp. 2313-2317, October 2007.
[11] G. Yang, Q. Zhu, J. Chi, and X. Zhuang, “A License Plate Recognition System Based on GFNN and DSP,” IEEE International Conference on Networking, Sensing and Control, pp. 160-164, April 2008.
[12] H. Fu and M. Xie, “Design and Realization of License Plate Recognition System Based on DSP and FPGA,” IEEE International Symposium on IT in Medicine and Education, pp. 39-43, December 2008.
[13] J.-M. Gao and Y.-F. Liu, “License Plate Localization and Character Segmentation with Feedback Self-Learning and Hybrid Binarization Techniques,” IEEE Transactions on Vehicular Technology, Vol. 57, No. 3, May 2008.
[14] M. Xie, H. Fu and Z. Liu, “One Design Method of License Plate Recognition System with High Recognition Rate,” IEEE International Symposium on IT in Medicine and Education, pp. 44-49, December 2008.
[15] Y. P. Huang, and T. Tsai, “A Practical License Plate Recognition System on PDA,” Int. Computer Symposium, pp. 731-736, December 2004.
[16] Z. W. Liu, H. D. Fu, and M. Xie, “Multiple Processors License Plate Recognition System for Intelligent Transportation Management,” Second International Symposium on Intelligent Information Technology Application, Vol. 1, pp. 333-336, December 2008.
[17] Texas Instruments Inc, TMS320DM6437 Evaluation Module Technical Reference, 2007.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top