LIN Mingru.Research of super-resolution image reconstruction in license plate recognition system[J].Journal of Yanbian University,2015,41(03):233-237.
车牌识别系统中的超分辨率图像重建技术研究䥺Symbol`@@
- Title:
- Research of super-resolution image reconstruction in license plate recognition system
- Keywords:
- super-resolution; image reconstruction; projection onto convex sets; license plate recognition
- 分类号:
- TP391.41
- 文献标志码:
- A
- 摘要:
- 针对车牌识别系统中图像模糊和分辨率低而影响车牌识别效果的问题,提出利用超分辨率重建来提高车牌图像分辨率的解决方法.建立了凸集投影(POCS)算法的数学模型,研究了凸集投影超分辨率重建的实现过程,并用仿真实验进行了验证.实验结果表明:采用凸集投影算法进行图像重建,可以提高车牌图像分辨率,丰富图像细节信息,能够有效提高车牌识别的准确率,并且迭代次数越多,图像重建效果越好.
- Abstract:
- In the license plate recognition system, blurred image and low resolution affect the effect of license plate recognition. A method which uses the super-resolution image reconstruction to improve the resolution of plate image is proposed. In this paper, mathematical model of projection onto convex sets(POCS)is established and the process of image reconstruction based on POCS is researched. Simulation experiments are conducted to verify the research. Experimental results show that,image reconstruction based on POCS algorithm can improve the resolution of license plate image, rich detail information of the image, enhance the vehicle license plate recognition system performance. Through the experiments, the more iterations are made, the better effects of image reconstruction appear.
参考文献/References:
[1] 林明儒.基于边缘分析和纹理信息统计的车牌定位研究[J].阜阳师范学院学报,2010,27(3):66-69.
[2] 李彦.探究车牌识别中的超分辨率算法[J].淮海工学院学报,2013,22(2):29-31.
[3] Yang Q X, Yang R G, Davis J, et al. Spatial depth super resolution for range images[C] //Proceedings of Computer Vision and Pattern Recognition Minneapolis. MN, USA: IEEE Computer Society Press, 2007.
[4] 吴炜,杨晓敏,卿粼波,等.基于马尔可夫随机场的低分辨率车牌图像复原算法[J].计算机应用研究,2010,27(3):1170-1172.
[5] 姚振杰,易卫东.一种用于车牌识别的图像超分辨率算法[J].中国科学院研究生院学报,2013,30(1):137-143.
[6] 李翠华,施华,戴平阳,等.引入格式塔理论的超分辨率图像重建技术[J].厦门大学学报,2011,50(2):261-270.
[7] 钟九生,江南,胡斌,等.一种遥感影像超分辨率重建的稀疏表示建模及算法[J].测绘学报,2014,43(3):276-283.
[8] 袁晶.基于超分辨重建数学模型的医学图像处理方法[J].计算机仿真,2014,31(5):243-245.
[9] Tsai R Y, Huang T S. Multiframe image restoration and registration[J].Advances in Computer Vision and Image Processing, 1984,1:317-339.
[10] 余永松,吴炜,陈为龙.基于凸集投影(POCS)的车牌图像超分辨率重建研究[J].计算机与数字工程,2009,37(2):139-142.
[11] 王茜艳,陈力,李萌.基于插值的图像修复算法[J].汕头大学学报,2015,30(2):72-80.
[12] 王春霞,苏红旗,范郭亮.图像超分辨率重建技术综述[J].计算机技术与发展,2011,21(5):124-127.
[13] 孙玉刚.数字图像修复技术研究[D].南京:南京航空航天大学,2011.
[14] 郭伟伟,章品正.基于迭代反投影的超分辨率图像重建[J].计算机科学与探索,2009,3(3):321-329.
[15] Kim K I, Kwon Y. Single-image super-resolution using sparse regression and natural image prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010,32(6):1127-1133.
[16] Sun J, Xu Z, Shum H Y. Gradient profile prior and its applications in image super-resolution and enhancement[J]. IEEE Transactions on Image Processing, 2011,20(6):1529-1542.
[17] 韩玉兵,束锋,孙锦涛,等.基于MG -GMRES算法的图像超分辨率重建[J].计算机学报,2007,30(6):1028-1034.
[18] 陈湘骥.基于多尺度相似学习的图像超分辨率重建算法研究[D].广州:华南理工大学,2014.
[19] Giachetti A, Asuni N. Real time artifact-free image up scaling[J].IEEE Transactions on Image Processing, 2011, 20(10):2760-2768.
[20] Yu J, Gao X, Tao D, et al. A unified learning framework for single image super-resolution[J]. IEEE Trans on Neural Networks and Learning Systems, 2014,25(4):780-792.
[21] 梅文兰.车牌识别中超分辨率算法的研究[D].成都:西南交通大学,2011.
备注/Memo
收稿日期: 2015-06-24 作者简介: 林明儒(1982—),男,高级工程师,研究方向为网络技术和模式识别.基金项目: 福建省教育厅科技研究项目(JB12290); 黎明职业大学校级课题研究项目(LZ2012102); 黎明职业大学科研团队建设项目(LMTD2014104)