CPU 기반의 딥러닝 컨볼루션 신경망을 이용한 이륜 차량 번호판 인식 알고리즘
Twowheeled Motor Vehicle License Plate Recognition Algorithm using CPU based Deep Learning Convolutional Neural Network
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Many research results on the traffic enforcement of illegal driving of twowheeled motor vehicles using license plate recognition are introduced. Deep learning convolutional neural networks can be used for character and word recognition of license plates because of better generalization capability compared to traditional Backpropagation neural networks. In the plates of twowheeled motor vehicles, the interdependent government and city words are included. If we implement the mutually independent word recognizers using error correction rules for two word recognition results, efficient license plate recognition results can be derived. The CPU based convolutional neural network without library under real time processing has an advantage of low cost real application compared to GPU based convolutional neural network with library. In this paper twowheeled motor vehicle license plate recognition algorithm is introduced using CPU based deep-learning convolutional neural network. The experimental results show that the proposed plate recognizer has 96.2% success rate for outdoor twowheeled motor vehicle images in real time.
Abstract
Many research results on the traffic enforcement of illegal driving of twowheeled motor vehicles using license plate recognition are introduced. Deep learning convolutional neural networks can be used for character and word recognition of license plates because of better generalization capability compared to traditional Backpropagation neural networks. In the plates of twowheeled motor vehicles, the interdependent government and city words are included. If we implement the mutually independent word recognizers using error correction rules for two word recognition results, efficient license plate recognition results can be derived. The CPU based convolutional neural network without library under real time processing has an advantage of low cost real application compared to GPU based convolutional neural network with library. In this paper twowheeled motor vehicle license plate recognition algorithm is introduced using CPU based deep-learning convolutional neural network. The experimental results show that the proposed plate recognizer has 96.2% success rate for outdoor twowheeled motor vehicle images in real time.
참고문헌 (11)
- 당순정, "YOLOv2 기반의 영상워핑을 이용한 강인한 오토바이 번호판 검출 및 인식", 방송공학회 논문지, 24(5), pp.713~725 (2019), 한국방송∙미디어공학회[DOI]
- D. How, "Character Recognition of Malaysian Vehicle License Plate with Deep Convolutional Neural Networks", IEEE Int. Symposium on Robotics and Intelligent Sensors, pp.1~5 (2016)
- "오토바이 무인 단속 추진" (2021), 박진형[URL]
- "TensorFlow 2 - CPU vs GPU Performance Comparison" (2019)[URL]
- 김진호, "딥러닝 신경망을 이용한 문자 및 단어 단위의 영문 차량 번호판 인식", (사)디지털산업정보학회 논문지, 16(4), pp.19~28 (2020), (사)디지털산업정보학회
- "Deep Learning Tutorial, Release 0.1, LISA Lab, U. of Montreal", ~ (2015)
- T. Liu, "Implementation of Training Convolutional Neural Networks", ~ (2015)
- Y. Sugomori, "Java Deep Learning Essentials" (2016), PACKET publishing
- 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. Tong, "Document Image Skew Correction Method based on Characteristic Sample Point Detection and Hough Transform", Journal of Convergence Information Technology, 7(22), pp.576~584 (2012)
- 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)