Real-Time Vehicle-Type Categorization and Character Extraction from the License Plates

  • Sneha Pavaskar
  • Suneeta BudihalEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 768)


Modern-day Intelligent Transportation System (ITS) needs heavy attention due to presence of existing infrastructure of roadways that is worsening with growing traffic. Thus, monitoring and controlling the traffic becomes a tedious task, hence automatic control is required rather than manual controlling. The vehicles are classified into the following types: Bike, Car, Auto-rickshaw, and HMV. Detection of vehicles is the main key task for the classification and also keeping a count of it. The proposed framework includes the vehicle-type classification by considering two features namely, contour formation for detection of vehicles and other is the concept of convex hull, which helps in classifying the vehicles. Text extraction from the vehicle license plates is another necessary task for ITS. KNN algorithm is used to create the xml les that is utilized to identify the characters and accordingly display it on the image and displays its effectiveness. This technique holds good for both single-lined and double-lined license plate reading efficiently, the concept of Tesseract-OCR is also used for character recognition and then the correctness is being compared for their effectiveness.


Convex Hull Heavy motor vehicles (HMV) Intelligent transport systems (ITS) K-Nearest neighbors (KNN) Tesseract-OCR (Optical character Recognition) 


  1. 1.
    Gupte, S., Masoud, O., Martin, R.F.K., Papanikolopoulos, N.P.: Detection and classification of vehicles. IEEE Trans. Intell. Transp. Syst. 3(1), 37–47 (2002)CrossRefGoogle Scholar
  2. 2.
    Baker, K.D., Sullivan, G.D.: Performance assessment of model-based tracking. In: Proceedings of IEEE Workshop Applications of Computer Vision, Palm Springs, CA, p. 2835 (1992)Google Scholar
  3. 3.
    Zhang, Z., Xu, C., Feng, W.: Road vehicle detection and classification based on deep neural network, acknowledged by National Natural Science Foundation of China. In: The Fundamental Research Funds for the Central Universities, IEEE, pp. 675–678 (In press, 2016)Google Scholar
  4. 4.
    Jiang, C., Zhang, B.: Weakly supervised vehicle detection and classification by convolutional neural network. In: 9th International Congress on Image and Signal Processing, Bio Medical Engineering and Informatics, pp 570–575 (2016)Google Scholar
  5. 5.
    Seenouvong, N., Watchareeruetai, U., Nuthong, C.: Vehicle detection and classification system based on virtual detection zone. In: 13th International Joint Conference on Computer Science and Software Engineering (JCSSE) (In press, 2016)Google Scholar
  6. 6.
    Chang, S.L., Chen, L.S., Chung, Y.C., Chen, S.W.: Automatic license plate recognition. IEEE Trans. Intell. Transp. Syst. 5(1), 42–53 (2004)CrossRefGoogle Scholar
  7. 7.
    Anagnostopoulos, C.N.E., Anagnostopoulos, I.E., Psoroulas, I.D., Loumos, V., Kayafas, E.: License plate recognition from still images and video sequences: a survey. IEEE Trans. Intell. Transp. Syst. 9(3), 377–391 (2008)CrossRefGoogle Scholar
  8. 8.
    Du, S., Ibrahim, M., Shehata, M., Badawy, W.: Automatic license plate recognition (ALPR): A state-of-the-art review. IEEE Trans. Circ. Syst. Video Technol. 23(2), 311–325 (2013)CrossRefGoogle Scholar
  9. 9.
    Puranic, A., Deepak, K.T., Umadevi, V.: Vehicle number plate recognition system: a literature review and implementation using template matching. Int. J. Comput. Appl. 134(1), 12–16 (2016)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.School of ECEKLE Technological UniversityHubballiIndia

Personalised recommendations