License Plate Detection and Recognition of Moving Vehicle Using Open CV
License plate detection and recognition system is to localize and extract license plate number of moving vehicle in real time environment. The system works on captured video stream of moving vehicle obtained from real working environments. This system is divided into four steps—video acquisition, vehicle detection, license plate detection, and character recognition. Detection of moving objects, i.e., vehicle in video streams is the first relevant step. For vehicle detection, we have used background subtraction method. Next step is license plate detection which is the process of finding license plate location in the image. For plate localization, several traditional image processing techniques are used such as image filtering, edge detection, morphological operations and contour detection; each plays an important role in the extraction process. The extracted license plates are segmented into individual characters by using a contour algorithm and centre line rule method. In this paper, character segmentation is used for correct license plate detection. This paper presents a new character recognition method which improves recognition accuracy of ambiguous characters. This method uses template matching algorithm and structural features of characters. This method improves accuracy as compared to previous template matching method. This paper presents a method for avoiding repetitive recognition of same license plate.
Cite this Article Yadav V, Bombale UL. License plate detection and recognition of moving vehicle using Open CV. Journal of Image Processing & Pattern Recognition Progress. 2016; 3(2): 32–42p.
Laganiere R. Background subtraction; Mixture of Gaussian; Optical flow. In: Opencv2 Computer vision application programming cookbook. Birmingham: Packt Publishing; 2011. 272–5p, 275–77p, 266–7p.
Shaikh S, Lahiri B, Bhatt G, et al. A novel approach for Automatic Number Plate Recognition. Proceedings of the International Conference on Intelligent Systems and Signal Processing (ISSP); 2013 Mar 1–2; Gujarat, India.
Gael S, Dabas S. Vehicle Registration Plate Recognition System Using Template Matching. Proceedings of International Conference on Signal Processing and Communication (ICSE); 2013 Dec 12–14; Noida, India.
Shantaiya S, Verma K, Mehta K. Study and Analysis of Methods of Object Detection in Video. IJSCE. 2013; 2(6): 173–5p.
Alex DS, Wahi A. BSFD: Background Subtraction Frame Difference Algorithm for Moving Object Detection and Extraction. Journal of Theoretical and Applied Information Technology. 2014; 60(3): 623– 8p.
Piccardi M. Background subtraction techniques: a review. Proceedings of the 2004 IEEE International Conference on Systems, Man and Cybernetics; 2004 Oct 10–13; The Hague.
Kaur H, Manvi, Singh B. Vehicle License Plate Detection from Video Using Edge Detection and Morphological Operators. IJERT. 2012; 1(9): 1–5p.
Sagar D, Dutta M. Block-Based Neural Network for Automatic Number Plate Recognition. IJSRP. 2014; 4(9): 1–7p.
Du S, Ibrahim M, Shehata M, et al. Automatic License Plate Recognition (ALPR): A State-of-the-Art Review. IEEE Transactions on Circuits and Systems for Video Technology. 2013; 23(2): 1–7p.
Shrivastava V, Sharma N. Artificial Neural Network Based Optical Character Recognition. Signal & Image Processing: An International Journal (SIPIJ). 2012; 3(5): 73–80p.
Draghici S. A neural network based artiﬁcial vision system for license plate recognition. Int J Neural Syst. 1997; 8(1): 113–26p.
Gonzalez RC, Woods RE. Mathematical Morphology, Segmentation, Thresholding, Object Recognition – Correlation. In: Digital Image Processing, 3rd Edn. USA: Pearson/Prentice Hall; 2008. 96–97p, 628– 35p, 700–25p, 738–42p, 866–72p.
Baggio DL, Levgen K, Emami S. Mastering OpenCV with practical computer vision projects. Birmingham: Packt Publishing Ltd.; 2012. 152–3p.
OpenCV_tutorial, Release 22.214.171.124. OpenCV [Internet]; Available from: www.opencv.org
- There are currently no refbacks.