The haze situation will seriously affect the quality of license plate recognition and reduce the performance of the visual processing algorithm. In order to improve the quality of haze pictures, a license plate recognition algorithm based on haze weather is proposed in this paper. The algorithm in this paper mainly consists of two parts: The first part is MPGAN image dehazing, which uses a generative adversarial network to dehaze the image, and combines multi-scale convolution and perceptual loss. Multi-scale convolution is conducive to better feature extraction. The perceptual loss makes up for the shortcoming that the mean square error (MSE) is greatly affected by outliers; the second part is to recognize the license plate, first we use YOLOv3 to locate the license plate, the STN network corrects the license plate, and finally enters the improved LPRNet network to get license plate information. Experimental results show that the dehazing model proposed in this paper achieves good results, and the evaluation indicators PSNR and SSIM are better than other representative algorithms. After comparing the license plate recognition algorithm with the LPRNet algorithm, the average accuracy rate can reach 93.9%.
Weiguo ZHANG
Xi'an University of Science and Technology
Jiaqi LU
Xi'an University of Science and Technology
Jing ZHANG
Xi'an University of Science and Technology
Xuewen LI
Xi'an University of Science and Technology
Qi ZHAO
Xi'an University of Science and Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Weiguo ZHANG, Jiaqi LU, Jing ZHANG, Xuewen LI, Qi ZHAO, "Research on the Algorithm of License Plate Recognition Based on MPGAN Haze Weather" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 5, pp. 1085-1093, May 2022, doi: 10.1587/transinf.2021EDP7178.
Abstract: The haze situation will seriously affect the quality of license plate recognition and reduce the performance of the visual processing algorithm. In order to improve the quality of haze pictures, a license plate recognition algorithm based on haze weather is proposed in this paper. The algorithm in this paper mainly consists of two parts: The first part is MPGAN image dehazing, which uses a generative adversarial network to dehaze the image, and combines multi-scale convolution and perceptual loss. Multi-scale convolution is conducive to better feature extraction. The perceptual loss makes up for the shortcoming that the mean square error (MSE) is greatly affected by outliers; the second part is to recognize the license plate, first we use YOLOv3 to locate the license plate, the STN network corrects the license plate, and finally enters the improved LPRNet network to get license plate information. Experimental results show that the dehazing model proposed in this paper achieves good results, and the evaluation indicators PSNR and SSIM are better than other representative algorithms. After comparing the license plate recognition algorithm with the LPRNet algorithm, the average accuracy rate can reach 93.9%.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDP7178/_p
Copy
@ARTICLE{e105-d_5_1085,
author={Weiguo ZHANG, Jiaqi LU, Jing ZHANG, Xuewen LI, Qi ZHAO, },
journal={IEICE TRANSACTIONS on Information},
title={Research on the Algorithm of License Plate Recognition Based on MPGAN Haze Weather},
year={2022},
volume={E105-D},
number={5},
pages={1085-1093},
abstract={The haze situation will seriously affect the quality of license plate recognition and reduce the performance of the visual processing algorithm. In order to improve the quality of haze pictures, a license plate recognition algorithm based on haze weather is proposed in this paper. The algorithm in this paper mainly consists of two parts: The first part is MPGAN image dehazing, which uses a generative adversarial network to dehaze the image, and combines multi-scale convolution and perceptual loss. Multi-scale convolution is conducive to better feature extraction. The perceptual loss makes up for the shortcoming that the mean square error (MSE) is greatly affected by outliers; the second part is to recognize the license plate, first we use YOLOv3 to locate the license plate, the STN network corrects the license plate, and finally enters the improved LPRNet network to get license plate information. Experimental results show that the dehazing model proposed in this paper achieves good results, and the evaluation indicators PSNR and SSIM are better than other representative algorithms. After comparing the license plate recognition algorithm with the LPRNet algorithm, the average accuracy rate can reach 93.9%.},
keywords={},
doi={10.1587/transinf.2021EDP7178},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Research on the Algorithm of License Plate Recognition Based on MPGAN Haze Weather
T2 - IEICE TRANSACTIONS on Information
SP - 1085
EP - 1093
AU - Weiguo ZHANG
AU - Jiaqi LU
AU - Jing ZHANG
AU - Xuewen LI
AU - Qi ZHAO
PY - 2022
DO - 10.1587/transinf.2021EDP7178
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2022
AB - The haze situation will seriously affect the quality of license plate recognition and reduce the performance of the visual processing algorithm. In order to improve the quality of haze pictures, a license plate recognition algorithm based on haze weather is proposed in this paper. The algorithm in this paper mainly consists of two parts: The first part is MPGAN image dehazing, which uses a generative adversarial network to dehaze the image, and combines multi-scale convolution and perceptual loss. Multi-scale convolution is conducive to better feature extraction. The perceptual loss makes up for the shortcoming that the mean square error (MSE) is greatly affected by outliers; the second part is to recognize the license plate, first we use YOLOv3 to locate the license plate, the STN network corrects the license plate, and finally enters the improved LPRNet network to get license plate information. Experimental results show that the dehazing model proposed in this paper achieves good results, and the evaluation indicators PSNR and SSIM are better than other representative algorithms. After comparing the license plate recognition algorithm with the LPRNet algorithm, the average accuracy rate can reach 93.9%.
ER -