8.1 結論
本研究目標為一即時性車牌辨識系統,透過改良 Stroke filter 達到即時性以及對於 車牌文字偵測上更好的效果,在配合後端 Adaboost 達到辨識之目的。經過大量實驗數 據測試後證明系統具有以下優點:
1.達到即時性:在軟體模擬演算法證實在高解析度下仍然壓在 1 秒以內,實作於硬 體架構速度則可達到即時影像偵測。
2.辨識率的提升:由於前端切割之文字較為完整,在辨識上,也提出一高速且辨識 率 90%以上之結果
3.對複雜環境的容忍度:相對於目前技術大多於固定角度單一車道之車牌偵測,本 系統對於真實環境也具有一定辨識程度,且對於背景影像中之文字也予以排除。
而在快速短線濾波器以及原本短線濾波器的效能上,其最大的改進為運算成本,在
效果上則為目標不同,所需要之靈敏度不同,故在效能上兩者的比較在於針對目標物的 種類而有所高低。
8.2 未來展望
在對於快速短線濾波器之設計,仍有改進的地方,針對變異數影響以及向量(scale) 上所能偵測的最小筆觸以及最大筆觸仍有爭議的空間,本次研究為了偵測車牌文字而針 對此訂出偵測值,若考慮到文字擷取以及偵測上之應用可以改良出一強快速短線濾波器 (robust fast stroke filter)。而在 line feature 上可能考慮提出一完整理論以證明校能接近或 者高於 haar-like feature,並且考慮針對人臉或者其他非二值化影像提出一特徵計算之演 算法。
本系統目前仍然為軟體模擬,未來希冀完成硬體部分的實作,初步期望能將其在 FPGA 板上實現,透過實際 CCD 從街道上擷取之影像,即時偵測車牌並且將擷取後之 文字影像經過 RS232 或者網路連接至電腦辨識,使其達到即時性的街道偵測,以及資訊 的截取,完成本次研究最大之目的:自動化車輛監控系統。
參考文獻
[1] A. K. Jain, B. Yu, Automatic text location in images and video frames, Pattern Recognition 31 (1998) 2055–2076.
[2] C. Jung, Q. Liu, J. Kim, A new approach for text segmentation using a stroke filter, Signal Processing, Elsevier 88(2008) 1907–1916.
[3] H. Li, D. Doermann, O. Kia, “Automatic text detection and tracking in digital video, IEEE Transactions on Image Processing 9 (1) (2000) 147–156.
[4] K.I. Kim, K. Jung, H. Kim, Texture-based approach for text detection in images using support vector machines and continuously adaptive mean shift algorithm, IEEE Transactions on Pattern Analysis and Matching Intelligence 25 (2003) 1631–1639.
[5] Louka Dlagnekov, “License Plate Detection Using AdaBoost”, Department for Computer Science & Engineering, La Jolla, CA 92093-0114.
[6] M. Lyu, J. Song, M. Cai, A Comprehensive Method for Multilingual Video Text Detection, Localization, and Extraction, IEEE Transactions on Circuits and Systems for Video Technology 15 (2005) 243–255.
[7] P. Viola, M. Jones, Rapid object detection using a boosted cascade of simple features, Conference on Computer Vision and Pattern Recognition (2001).
[8] P. Viola, M. Jones, Roust real-time face detection, International Journal of Computer Vision 57 (2004) 137–154.
[9] Q. Ye, Q. Huang, W. Gao, D. Zhao, Fast and robust text detection in images and video frames, Image and Vision Computing 23 (2005) 565–576.
[10] Q. Liu, C. Jung, S. Kim, Y. Moon, J. Kim, Stroke filter for text localization in video images, Proc. Int. Conf. Image Process. (2006) 1473–1476.
[11] Q. Liu, Ch. Jung, Y. Moon, Text Segmentation based on Stroke Filter, Proceedings of ACM international conference on Multimedia (2006) 129-132.
[12] R. Lienhart, A. Wernicke, Localizing and Segmenting Text in Images and Videos, IEEE Transactions on Circuits and Systems for Video Technology 12 (4) (2002) 256–268.
[13] R. Lienhart, J. Maydt, An extended set of haar-like features for rapid object detection, IEEE ICIP 1 (2002) 900–903.
[14] R. Lienhart, A. Kuranov, V. Pisarevsky, Empirical analysis of detection cascades of boosted classifiers for rapid object detection, MRL Technical Report (2002).
[15] T. Sato, T. Kanade, E. K. Hughes, M. A. Smith, Video OCR for digital news archive, Proc. IEEE Workshop on Content-Based Access of Image and Video Database (1998) 52–60.
[16] V. Wu, R. Manmatha, E.M. Riseman, Finding text in images, Proceedings of the second ACM international conference on Digital libraries (1997) 23–26.
[17] V. Wu, R. Manmatha, E. M. Riseman, Textfinder: An automatic system to detect and recognize text in images, IEEE Transactions on Pattern Analysis and Matching Intelligence 21 (11) (1999) 1224–1229.
附錄 A Stroke Filter 比較圖
附錄 A 中附加 50 張車牌原始 Stroke filter 以及 Fast Stroke Filter 比較圖 其中最上為輸入車牌,中間為原始 Stroke filter,最下為 Fast Stroke Filter