一种基于MSER和SWT的新型车牌检测识别方法研究
|
摘要
为了降低拍摄距离、光照等对车牌识别的影响,提高复杂背景下车牌识别准确率,提出了一种基于最大极值稳定区域(maximally stable extremal regions,MSER)和笔画宽度变换(stroke width transform,SWT)的新型车牌检测识别方法。该方法首先进行MSER提取和Canny边缘检测,并根据车牌字符特征对二者相与运算后的MSER筛选;然后在筛选后的区域内做基于形态学处理的SWT和SW筛选,聚合筛选后区域,结合车牌几何特征完成车牌精定位;最后校正分割定位成功区域内连通域,提取骨架并归一化,与细化和归一化后的模板匹配。利用HU不变矩和网格特征识别首字符汉字,采用扫描跳跃点统计编码识别数字和字母。实验结果表明:该方法定位准确率高达94. 86%,识别准确率达96. 14%。该方法对远距离、变光照获取的复杂背景下,车牌检测识别具有较高的准确率和鲁棒性。
In order to reduce the influence of camera distance and the light on license plate recognition,improving the recognition accuracy of license plate with complex background,a new license plate recognition method based on maximally stable extremal regions( MSER) and stroke width transform( SWT) has been proposed. Firstly,the MSER extraction and Canny edge detection are carried out and the filter of the MSER based on geometric features of license plate character is conducted,then the SWT and SW selection of the selected areas is conducted based on morphological processing,the selected regions are gathered and the license plate is located combined with their features. Finally,the segmentation of the location region is checked and its skeleton are extracted and normalized,then,it is matched with the thinned and normalized template. The first character Chinese characters are recognized by HU invariant moments and grid features,and the digits and letters are identified by scanning skip point statistics code. Experiment results show that the accuracy of the location is as high as 94. 86% and the accuracyof the recognition is as high as 96. 92%,which indicates that this method has high accuracy and robustness for license plate detection and recognition in complex background with long distance and variable illumination.
In order to reduce the influence of camera distance and the light on license plate recognition,improving the recognition accuracy of license plate with complex background,a new license plate recognition method based on maximally stable extremal regions( MSER) and stroke width transform( SWT) has been proposed. Firstly,the MSER extraction and Canny edge detection are carried out and the filter of the MSER based on geometric features of license plate character is conducted,then the SWT and SW selection of the selected areas is conducted based on morphological processing,the selected regions are gathered and the license plate is located combined with their features. Finally,the segmentation of the location region is checked and its skeleton are extracted and normalized,then,it is matched with the thinned and normalized template. The first character Chinese characters are recognized by HU invariant moments and grid features,and the digits and letters are identified by scanning skip point statistics code. Experiment results show that the accuracy of the location is as high as 94. 86% and the accuracyof the recognition is as high as 96. 92%,which indicates that this method has high accuracy and robustness for license plate detection and recognition in complex background with long distance and variable illumination.
引文
[1]万燕,徐勤燕,黄蒙蒙.复杂背景中基于纹理和颜色的车牌定位研究[J].计算机应用与软件,2013,30(10):259-262.Wan Y,Xu Q Y,Huang M M. On License Plate Location in Complex Background Based on Texture and Colour[J]. Computer Applications and Software, 2013,30(10):259-262.
[2]李林青,彭进业,冯晓毅.基于边缘分析和颜色统计的车牌精定位新方法[J].计算机应用研究,2012,29(1):336-339,343.Li L Q,Peng J Y,Feng X Y. New approach for precise license plate locating based on edge analysis and color statistics[J]. Application Research of Computers,2012,29(1):336-339,343.
[3] Rajput H,Som T. An automated vehicle license plate recognition system[J]. Computing Practices, 2015,48(8):56-61.
[4]周律,汪亮,周昱明.基于固定颜色搭配搜索和形态学的车牌定位[J].公路交通科技,2013,30(5):118-125.Zhou L,Wang L,Zhou Y M,et al. License Plate Location Based on Fixed Color Assortment Search and Morphology[J]. Journal of Highway and Transportation Research and Development,2013,30(5):118-125.
[5]冉令峰.基于垂直投影的车牌字符分割方法[J].通信技术,2012,45(4):89-91,98.Ran L F. An Algorithm of Characters Segmentation based on Vertical Projection for License Plate[J].Communications Technology,2012,45(4):89-91,98.
[6]陈艳,孙羽菲,张玉志.基于连通域的汉字切分技术研究[J].计算机应用研究,2005,22(6):246-248.Chen Y, Sun Y F, Zhang Y Z. Chinese Character Segmentation Technique Based on Interconnected Domain[J]. Application Research of Computers,2005,22(6):246-248.
[7] Gao Q,Wang X,Xie G. License Plate Recognition Based On Prior Knowledge[C]//IEEE International Conference on Automation and Logistics. IEEE,2007:2964-2968.
[8]高聪,王福龙.基于模板匹配和局部HOG特征的车牌识别算法[J].计算机系统应用,2017,26(1):122-126.Gao C, Wang F L. Algorithm of License Plate Recognition Based on Template Matching and Local HOG Feature[J]. Computer Systems&Applications,2017,26(1):122-126.
[9] Huang L,Yang T J. Vehicle license plate recognition based on wavelet transform modulus and BP neural network[C]//IEEE. International Conference on Natural Computation. 2012:295-297.
[10]程淑红,高许,周斌.基于多特征提取和SVM参数优化的车型识别[J].计量学报,2018,39(03):348-352.Cheng S H,Gao X,Zhou B. Vehicle Recognition Based on Multi-feature Extraction and SVM Parameter Optimization[J]. Acta Metrologica Sinica,2018,39(3):348-352.
[11] Li B,Tian B,Yao Q,et al. A vehicle license plate recognition system based on analysis of maximally stable extremal regions[C]//IEEE International Conference on Networking,Sensing and Control. IEEE,2012; 399-404.
[12] Gou C,Wang K F,Yao Y J,et al. Vehicle license plate recognition based on extremal regions and restricted Boltzmann machines[J]. IEEE Transactions on intelligent transportation systems,2016,4(17):1096-1107.
[13] Epshtein B, Ofek E, Wexler Y. Detecting text in natural scenes with stroke width transform[C]//IEEE Conference on Computer Vision and Pattern Recognition. 2010,119(5):2963-2970.
[14] Hu M K. Visual pattern recognition by moment invariants[J]. Information Theory Ire Transactions on,1962,8(2):179-187.
[15]程一峰,刘增力.改进的K-奇异值分解图像去噪算法[J].计量学报,2018,39(3):332-336.Cheng Y F,Liu Z L. Improved K-SVD Image Denoising Algorithm[J]. Acta Metrologaca Sinica,2018,39(3):332-336.
[16]杨丹凤,吕岳.方向特征和网格特征融合的离线签名鉴别[J].中国图象图形学报,2012,17(6):717-721.Yang D F,Lv Y. Off-line signature verification based on combination of direction feature and grid feature[J].Journal of Image and Graphics,2012,17(6):717-721.
[17]廖素引,吴博,卫敏.彩色伪随机编码图像特征点神经网络匹配[J].计量学报,2016,37(5):494-498.Liao S Y, Wu B, Wei M. Pseudo Random Color Encoded Image Feature Points Matching Based on Neural Network[J]. Acta Metrologica Sinica,2016,37(5):494-498.
[18]程淑红,高许,程树春,等.基于计算机视觉的运动车辆检测[J].计量学报,2017,38(3):288-291.Cheng S H,Gao X,Cheng S C. Moving Vehicle Detection Based on Computer Vision[J]. Acta Metrologica Sinica,2017,38(3):288-291.
[19]吴凤和.基于计算机视觉测量技术的图像轮廓提取方法研究[J].计量学报,2007,28(1):18-22.Wu F H. A study on contour extraction method in computer vision measyrement tachology[J]. Acta Metrologica Sinica,2007,28(1):18-22.
[20]苗立刚.基于最近邻链的车牌检测算法[J].自动化学报,2011,37(10):1272-1280.Miao L G. License plate detection algorithm based on nearest neighbor chains[J]. Acta Automatica Sinica,2011,37(10):1272-1280.
[2]李林青,彭进业,冯晓毅.基于边缘分析和颜色统计的车牌精定位新方法[J].计算机应用研究,2012,29(1):336-339,343.Li L Q,Peng J Y,Feng X Y. New approach for precise license plate locating based on edge analysis and color statistics[J]. Application Research of Computers,2012,29(1):336-339,343.
[3] Rajput H,Som T. An automated vehicle license plate recognition system[J]. Computing Practices, 2015,48(8):56-61.
[4]周律,汪亮,周昱明.基于固定颜色搭配搜索和形态学的车牌定位[J].公路交通科技,2013,30(5):118-125.Zhou L,Wang L,Zhou Y M,et al. License Plate Location Based on Fixed Color Assortment Search and Morphology[J]. Journal of Highway and Transportation Research and Development,2013,30(5):118-125.
[5]冉令峰.基于垂直投影的车牌字符分割方法[J].通信技术,2012,45(4):89-91,98.Ran L F. An Algorithm of Characters Segmentation based on Vertical Projection for License Plate[J].Communications Technology,2012,45(4):89-91,98.
[6]陈艳,孙羽菲,张玉志.基于连通域的汉字切分技术研究[J].计算机应用研究,2005,22(6):246-248.Chen Y, Sun Y F, Zhang Y Z. Chinese Character Segmentation Technique Based on Interconnected Domain[J]. Application Research of Computers,2005,22(6):246-248.
[7] Gao Q,Wang X,Xie G. License Plate Recognition Based On Prior Knowledge[C]//IEEE International Conference on Automation and Logistics. IEEE,2007:2964-2968.
[8]高聪,王福龙.基于模板匹配和局部HOG特征的车牌识别算法[J].计算机系统应用,2017,26(1):122-126.Gao C, Wang F L. Algorithm of License Plate Recognition Based on Template Matching and Local HOG Feature[J]. Computer Systems&Applications,2017,26(1):122-126.
[9] Huang L,Yang T J. Vehicle license plate recognition based on wavelet transform modulus and BP neural network[C]//IEEE. International Conference on Natural Computation. 2012:295-297.
[10]程淑红,高许,周斌.基于多特征提取和SVM参数优化的车型识别[J].计量学报,2018,39(03):348-352.Cheng S H,Gao X,Zhou B. Vehicle Recognition Based on Multi-feature Extraction and SVM Parameter Optimization[J]. Acta Metrologica Sinica,2018,39(3):348-352.
[11] Li B,Tian B,Yao Q,et al. A vehicle license plate recognition system based on analysis of maximally stable extremal regions[C]//IEEE International Conference on Networking,Sensing and Control. IEEE,2012; 399-404.
[12] Gou C,Wang K F,Yao Y J,et al. Vehicle license plate recognition based on extremal regions and restricted Boltzmann machines[J]. IEEE Transactions on intelligent transportation systems,2016,4(17):1096-1107.
[13] Epshtein B, Ofek E, Wexler Y. Detecting text in natural scenes with stroke width transform[C]//IEEE Conference on Computer Vision and Pattern Recognition. 2010,119(5):2963-2970.
[14] Hu M K. Visual pattern recognition by moment invariants[J]. Information Theory Ire Transactions on,1962,8(2):179-187.
[15]程一峰,刘增力.改进的K-奇异值分解图像去噪算法[J].计量学报,2018,39(3):332-336.Cheng Y F,Liu Z L. Improved K-SVD Image Denoising Algorithm[J]. Acta Metrologaca Sinica,2018,39(3):332-336.
[16]杨丹凤,吕岳.方向特征和网格特征融合的离线签名鉴别[J].中国图象图形学报,2012,17(6):717-721.Yang D F,Lv Y. Off-line signature verification based on combination of direction feature and grid feature[J].Journal of Image and Graphics,2012,17(6):717-721.
[17]廖素引,吴博,卫敏.彩色伪随机编码图像特征点神经网络匹配[J].计量学报,2016,37(5):494-498.Liao S Y, Wu B, Wei M. Pseudo Random Color Encoded Image Feature Points Matching Based on Neural Network[J]. Acta Metrologica Sinica,2016,37(5):494-498.
[18]程淑红,高许,程树春,等.基于计算机视觉的运动车辆检测[J].计量学报,2017,38(3):288-291.Cheng S H,Gao X,Cheng S C. Moving Vehicle Detection Based on Computer Vision[J]. Acta Metrologica Sinica,2017,38(3):288-291.
[19]吴凤和.基于计算机视觉测量技术的图像轮廓提取方法研究[J].计量学报,2007,28(1):18-22.Wu F H. A study on contour extraction method in computer vision measyrement tachology[J]. Acta Metrologica Sinica,2007,28(1):18-22.
[20]苗立刚.基于最近邻链的车牌检测算法[J].自动化学报,2011,37(10):1272-1280.Miao L G. License plate detection algorithm based on nearest neighbor chains[J]. Acta Automatica Sinica,2011,37(10):1272-1280.