딥러닝 신경망을 이용한 문자 및 단어 단위의 영문 차량 번호판 인식
Character Level and Word Level English License Plate Recognition Using Deep-learning Neural Networks
1
조회
0
다운로드
5
인용
0
참고문헌
키워드
초록
Vehicle license plate recognition system is not generalized in Malaysia due to the loose character layout rule and the varying number of characters as well as the mixed capital English characters and italic English words. Because the italic English word is hard to segmentation, a separate method is required to recognize in Malaysian license plate. In this paper, we propose a mixed character level and word level English license plate recognition algorithm using deep learning neural networks. The difference of Gaussian method is used to segment character and word by generating a black and white image with emphasized character strokes and separated touching characters. The proposed deep learning neural networks are implemented on the LPR system at the gate of a building in Kuala-Lumpur for the collection of database and the evaluation of algorithm performance. The evaluation results show that the proposed Malaysian English LPR can be used in commercial market with 98.01% accuracy.
Abstract
Vehicle license plate recognition system is not generalized in Malaysia due to the loose character layout rule and the varying number of characters as well as the mixed capital English characters and italic English words. Because the italic English word is hard to segmentation, a separate method is required to recognize in Malaysian license plate. In this paper, we propose a mixed character level and word level English license plate recognition algorithm using deep learning neural networks. The difference of Gaussian method is used to segment character and word by generating a black and white image with emphasized character strokes and separated touching characters. The proposed deep learning neural networks are implemented on the LPR system at the gate of a building in Kuala-Lumpur for the collection of database and the evaluation of algorithm performance. The evaluation results show that the proposed Malaysian English LPR can be used in commercial market with 98.01% accuracy.
참고문헌 (11)
- H. Ng, "Detection and Recognition of Malaysian Special License Plate Based on SIFT Features", Computer Vision and Pattern Recognition (CVPR), pp.321~329 (2015)
- M. Rahman, "Software Development Of A License Plate Recognition System", SDIWC (2015)
- D. How, "Character Recognition of Malaysian Vehicle License Plate with Deep Convolutional Neural Networks", IEEE International Symposium on Robotics and Intelligent Sensors, pp.1~5 (2016)
- M. Olatunde, "An Automatic Technique for Malaysian Number Plate Recognition", Master, pp.2018
- Y. Choong, "License Plate Number Detection and Recognition Using Simplified Linear-Model", Journal of critical reviews, 7(3), pp.55~60 (2020)
- G. Sarker, "A Convolution Neural Network for Optical Character Recognition and Subsequent Machine Translation", Int. Journal of Computer Application, 182(30), pp.23~27 (2018)
- L. Assirati, "Performing edge detection by Difference of Gaussians using q-Gaussian kernels", 2nd Int. Conf. on Mathematical Modeling in Physical Sciences, pp.1~4 (2013)
- G. Kiran, "Automatic Rectification of Perspective Distortion from a Single Image Using Plane Homography", Int. J. of Computational Sciences & Applications, 3(5), pp.47~58 (2013)
- "Deep Learning Tutorial, Release 0.1", LISA Lab, U. of Montreal, ~ (2015)
- T. Liu, "Implementation of Training Convolutional Neural Networks", arXiv : 1506. 01195v2, ~ (2015)
- Y. Sugomori, "Java Deep Learning Essentials" (2016), PACKET publishing