DOIONLINE

DOIONLINE NO - IJEEDC-IRAJ-DOIONLINE-16689

Publish In
International Journal of Electrical, Electronics and Data Communication (IJEEDC)-IJEEDC
Journal Home
Volume Issue
Issue
Volume-7,Issue-12  ( Dec, 2019 )
Paper Title
Yolo-Based Method For Indian Car License Plate Detection
Author Name
Monal Patel, Arvind Yadav, Carlos Valderrama
Affilition
Dept. of Electronics and Communication Parul Institute of Engineering and Technology, Parul University, Vadodara, Gujarat, India Dept. of Electronics and Microelectronics University of Mons, Mons, Belgium, Europe
Pages
1-5
Abstract
This paper presents a novel convolutional neural network (CNN) YOLO-based technique for high-accuracy real time Indian car license plate detection. Several methods for car license plate detection are reasonably effective under the specific conditions or strong assumptions only. However, they exhibit poor performance once the assessed car license plate images have a degree of rotation, as a result of manual capture by traffic police or deviation of the camera. Therefore, in this work we have proposed CNN-based YOLO framework for Indian car license plate detection. Using accurate prediction and a fast intersection-over-union evaluation strategy, our proposed method can elegantly manage problems in real time scenarios. A series of experiments have been carried out to establish that the proposed method outperforms other existing state-of-the-art methods in terms of higher accuracy and lower computational cost. Keywords - License Plate Detection, Convolutional Neural Network, YOLO, Multi-Direction Indian License Plate.
  View Paper