交通标志检测与识别技术研究
|
摘要
随着科技的发展和人们生活水平的不断提高,公路上各种车辆的数量与日俱增,这给人们的生活带来了极大的便利,同时交通事故问题也越来越严重。引发交通事故的因素为驾驶员错误操作、路况不好、天气影响等。据统计80%的交通事故归咎于驾驶员误操作。为了降低交通事故率,道路交通标志识别系统TSR (Traffic Signs Recognition)应运而生。道路交通标志识别系统识别交通标志并反馈给驾驶员可以使驾驶员提前了解路况及其变化并及时做出正确的反应措施,从而尽量减少交通事故的发生。
在道路交通标志中,常见的是警告、指示和禁令交通标志,每类交通标志都由特定颜色和形状的图案、文字构成。当外界光照强度发生变化、天气变化,交通标志牌倾斜,采集到的交通标志存在尺度变化都会影响道路交通标志识别系统的识别效果。所以,需要使识别系统具有旋转、尺度不变性。另外,在图像采集过程中容易混入噪声,所以系统需要具有抗噪性。
道路交通标志识别系统主要包括交通标志采集、预处理、检测和识别。采集并识别不同光照条件下的道路交通标志可以验证道路交通识别系统的稳定性。为了降低光照强度对道路交通标志图像带来的影响,本文应用HSI彩色空间图像增强。在道路交通标志检测过程中,根据交通标志的颜色特性,在Lab彩色空间中应用Mean shift图像分割算法,从而将道路交通标志从自然场景中分离出来。对数极坐标变换(LPT)与离散傅里叶变换(DFT)相结合的方法(LPT-DFT)具有旋转和尺度不变性。Contourlet变换和双数复小波变换都具有良好的多分辨率、多方向性并常应用于纹理特征提取。本文提出LPT-DFT分别与Contourlet变换、双树复小波变换(DT-CWT)结合的方法并应用Brodatz纹理图像库和交通标志图像库验证了这两种方法具有良好的旋转不变性、尺度不变性和抗噪性。另外,本文提出基于颜色直方图和纹理相结合的方法进行特征提取并通过应用模板匹配法对交通标志分类识别,通过实验进一步证明这两种方法能够有效的实现交通标志分类识别。
With the development of technology and the increased living standards of the people, the number of private car on the highway is growing with each passing day. While the development of transportation has brought great convenience for people, at the same time the problems caused by traffic accidents become more and more serious. The factors that cause the traffic accident include the drivers'error, the weather conditions and so on. According to statistics,80%of the traffic accidents result from the misoperation of driver. In order to reduce the rate of traffic accidents, Traffic Signs Recognition System emerges. The traffic signs recognition system can recognize the traffic sign and then give the driver feedback that allows the driver timely response measures to correct under the changes of the road conditions so as to reduce the traffic accident.
The most common types of the traffic signs are warning signs, the directional signs and the prohibition signs. Each type of traffic sign is composed of patterns and characters which have certain colors and shapes. When the illumination intensity or the weather changes, the traffic signs tilt or the collected traffic signs have scale change, they all could affect the recognition effect of the traffic sign recognition system. So the traffic signs recognition system should be of rotation, scale invariance. In addition, the image you grabbed easily contains noise signals, so the system needs to have anti-noise property. In the process of processing image, we use image enhance in the HSI Color Space to reduce the effect of the changes of illumination intensity.
Road traffic sign recognition system mainly includes road traffic sign collecting, image preprocessing, image detecting and recognition. By Collecting and recognizing the road traffic signs in different light conditions can verify the stability of the traffic sign recognition system. In order to reduce impacts on the image of road traffic sign from illumination intensity, this paper applied the HSI color space of image enhancement, by the processing of luminance and saturation component so that the image for subsequent processing. In the process road traffic sign, according to the color characteristics of traffic signs, the application of Mean shift image in Lab color space segmentation algorithm, which will be road traffic signs from natural scenes. The combination of log-polar transform and Discrete Fourier Transform (LPT-DFT) has the prosperities of scale and rotation invariance. Contourlet transform and Dual-Tree Complex Wavelet Transform (DT-CWT) possess good multi-resolution and multi-direction, and then they are usually used to extract the texture feature vector. In this paper the method combined by the transformations from LPT-DFT to Contourlet transform and DT-CWT respectively and its applications to Brodatz texture image database verify the advantages, such as scale invariance, rotation invariance and anti-noise property. In addition,the method of combining two kinds of feature extraction based on texture and feature extraction based on color histogram method is used, and then template matching is applied to recognize road traffic sign. The experiments results demonstrate that the methods can effectively recognize the road traffic signs.
在道路交通标志中,常见的是警告、指示和禁令交通标志,每类交通标志都由特定颜色和形状的图案、文字构成。当外界光照强度发生变化、天气变化,交通标志牌倾斜,采集到的交通标志存在尺度变化都会影响道路交通标志识别系统的识别效果。所以,需要使识别系统具有旋转、尺度不变性。另外,在图像采集过程中容易混入噪声,所以系统需要具有抗噪性。
道路交通标志识别系统主要包括交通标志采集、预处理、检测和识别。采集并识别不同光照条件下的道路交通标志可以验证道路交通识别系统的稳定性。为了降低光照强度对道路交通标志图像带来的影响,本文应用HSI彩色空间图像增强。在道路交通标志检测过程中,根据交通标志的颜色特性,在Lab彩色空间中应用Mean shift图像分割算法,从而将道路交通标志从自然场景中分离出来。对数极坐标变换(LPT)与离散傅里叶变换(DFT)相结合的方法(LPT-DFT)具有旋转和尺度不变性。Contourlet变换和双数复小波变换都具有良好的多分辨率、多方向性并常应用于纹理特征提取。本文提出LPT-DFT分别与Contourlet变换、双树复小波变换(DT-CWT)结合的方法并应用Brodatz纹理图像库和交通标志图像库验证了这两种方法具有良好的旋转不变性、尺度不变性和抗噪性。另外,本文提出基于颜色直方图和纹理相结合的方法进行特征提取并通过应用模板匹配法对交通标志分类识别,通过实验进一步证明这两种方法能够有效的实现交通标志分类识别。
With the development of technology and the increased living standards of the people, the number of private car on the highway is growing with each passing day. While the development of transportation has brought great convenience for people, at the same time the problems caused by traffic accidents become more and more serious. The factors that cause the traffic accident include the drivers'error, the weather conditions and so on. According to statistics,80%of the traffic accidents result from the misoperation of driver. In order to reduce the rate of traffic accidents, Traffic Signs Recognition System emerges. The traffic signs recognition system can recognize the traffic sign and then give the driver feedback that allows the driver timely response measures to correct under the changes of the road conditions so as to reduce the traffic accident.
The most common types of the traffic signs are warning signs, the directional signs and the prohibition signs. Each type of traffic sign is composed of patterns and characters which have certain colors and shapes. When the illumination intensity or the weather changes, the traffic signs tilt or the collected traffic signs have scale change, they all could affect the recognition effect of the traffic sign recognition system. So the traffic signs recognition system should be of rotation, scale invariance. In addition, the image you grabbed easily contains noise signals, so the system needs to have anti-noise property. In the process of processing image, we use image enhance in the HSI Color Space to reduce the effect of the changes of illumination intensity.
Road traffic sign recognition system mainly includes road traffic sign collecting, image preprocessing, image detecting and recognition. By Collecting and recognizing the road traffic signs in different light conditions can verify the stability of the traffic sign recognition system. In order to reduce impacts on the image of road traffic sign from illumination intensity, this paper applied the HSI color space of image enhancement, by the processing of luminance and saturation component so that the image for subsequent processing. In the process road traffic sign, according to the color characteristics of traffic signs, the application of Mean shift image in Lab color space segmentation algorithm, which will be road traffic signs from natural scenes. The combination of log-polar transform and Discrete Fourier Transform (LPT-DFT) has the prosperities of scale and rotation invariance. Contourlet transform and Dual-Tree Complex Wavelet Transform (DT-CWT) possess good multi-resolution and multi-direction, and then they are usually used to extract the texture feature vector. In this paper the method combined by the transformations from LPT-DFT to Contourlet transform and DT-CWT respectively and its applications to Brodatz texture image database verify the advantages, such as scale invariance, rotation invariance and anti-noise property. In addition,the method of combining two kinds of feature extraction based on texture and feature extraction based on color histogram method is used, and then template matching is applied to recognize road traffic sign. The experiments results demonstrate that the methods can effectively recognize the road traffic signs.
引文
[1]http://wenku.baidu.com/view/fa6ad4a3f524ccbffl21847d.html
[2]Hu S H, Huang C L. Road Sign Detection and Recognition Using Matching Pursuit Method [J]. Image and Vision Computing,2001,19(3):120-129.
[3]邵桂珠.道路交通标志识别算法的研究[硕士论文].吉林：吉林大学.2008.
[4]M. de, Saint Blancard. Road sign recognition:A study of vision-based decision making for road environment recognition[J]. Vision-based Vehicle Guidance, Springer Series in Perception Engineering,1992,pp:162-172..
[5]N. Kehtarnavaz, N. C. Griswold, D. S. Kang. Stop-sign recognition based on color shape processing. Machine Vision and Applications,1993,pp:206-208.
[6]L. Priese, J. Klieber, R. Lakmann, V. Rehrmann, R. Schian. New results on traffic sign recognition. In IEEE Proc. Intelligent Vehicle'94 Symposium,1994,pp:249-253.
[7]Jun Miura, Tsuyoshi Kanda, Yoshiaki shirai. An Active Vision System for Real-Time Traffic Sign Recognition.Proe.2000 IEEE Int. Conf. On Intelligent Transportation Systems, Dearbom, ML. USA,2000,pp:52-57.
[8]Henry X. Liu, Bin Ran. Vision-Based Stop Sign Detection and Recognition System for Intelligent Vehicles [J]. Transportation Research Record,2001,1748:161-166.
[9]Jun Miura, Tsuyoshi Kanda, Yoshiaki Shirai. An Active Vision System for Read Time Traffic Sign Recognition.Proc.2000 IEEE Int. Conf. On Intelligent Transportation Systems,2000:52-57.
[10]蒋刚毅,郑义.形态骨架匹配算法及其在交通标志识别中的应用[J].电路与系统学报,1996,1(3)：16-23.
[11]朱双东,张懿,陆晓峰.三角形交通标志的智能检测方法[J].中国图像图形学报,2006,11(8)：161-166.
[12]朱双东,刘兰兰,陆晓峰.一种用于道路交通标志识别的颜色-几何模型[J].仪器仪表学报,2007,28(5)：956-960.
[13]姚敏.数字图像处理[M],北京：机械工业出版社,2006,122-224.
[14]Shadeed, etal. Road traffic sign detection in color images. Electronics, Circuits and Systems, 2003.ICECS2003.Proeeedings of the 2003 Iota IEEE International Conference on,2003,pp:890-893.
[15]王萍,程号,罗颖听.基于色调不变的彩色图像增强[J].中国图像图形学报,2007,12(7)：1173-1178.
[16]Rafael C. Gonzalez, Richard E. Woods. Digital Image processing (Second Edition)[M]. Publishing House of Electronics Industry.2008,pp:235-236.
[17]C.冈萨雷斯,阮秋琦,阮宁智等译.数字图像处理[M].北京：电子工业出版社,2003,pp：91-112.
[18]Mean shift:a robust approach toward feature space analysis, D Comaniciu, P Meer Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol.24, No.5.2002, pp.603-619.
[19]D.Comaniciu, V. Ramesh, and P. Meer, "Real-Time Tracking of Non-Rigid Objecets Using Mean Shift," Proc.2000 IEEE Conf. Computer Vision and Pattern Recognition, vol. II, 2000,pp:142-149.
[20]朱胜利Mean Shift及相关算法在视频跟踪中的研究[博士学位论文].杭州：浙江大学,2006.
[21]张娟.基于彩色图像分割的立体匹配算法研究.[硕士论文],山东大学,2007.
[22]胡小锋,赵辉Visual C++/MATLAB图像处理与识别[M].北京：人民邮电出版社.2004.
[23]Rodrigues, M. A. Liu, Y. Motion Parameter Constraints Analysis from a Single Image. International Conference of IEEE on Image Processing,1999, pp:704-708.
[24]Jacinto Nascimento,Arnaldo,J.Abrantes,Jorge S.Marques.Using Middle Level Features for Robust Shape Tracking.Pattern Recognition Letters,2003,pp:295-307
[25]D. Gabor, "Theory of communication," IEEE Trans. Information Theory, Vol.9, No.3, 1946,pp.76-87.
[26]Mohammad A. Tinati, Behzad Mozaffary, "Comparison of the wavelet and short time Fourier transforms for spectral analysis of speech signals," in Proc. the 5th WSEAS,2005,pp.31-35.
[27]Abdul-Rahman A, Hailes S.A Distributed Trust Model[C].In the Proceeding of the 1997 New Security Paradigms Workshop, Cumbria, UK:ACM Press,1998,pp:48-60.
[28]王卫卫,杨波,宋国乡.图像可靠性鉴定的数字水印算法[J].西安：西安电子科技大学学报,2001,28(4)：507-511.
[29]N G Kingsbury. The dual-tree complex wavelet transform:a new efficient tool for image restoration and enhancement, Proc. European Signal Processing Conference, EUSIPCO 98, Rhodes,1998, pp:319-322.
[30]J F A Magarey, N G Kingsbury. Motion estimation using a complex-valued wavelet transform, IEEE Trans, on Signal Processing,1998,pp:1069-84
[31]N. Kingsbury. Image processing with complex wavelets, Phil. Tran. R. Soc. Lond. A, 1999,pp:2543-2560
[32]N. Kingsbury, Complex wavelets for shift invariant analysis and filtering of signals, Appli.Comput.Harmon.Anal.,2001,pp:234-253
[33]H. Choi, J. Romberg, R. G. Baraniuk, N. Kingsbury. "Hidden Markov tree modeling of complex wavelet transforms," in Proc. ICASSP,2000,pp:133-136.
[34]P. F. C. de Rivaz, N. G. Kingsbury, "Complex wavelet features for fast texture image retrieval," in Proc. IEEE Int. Conf. Image Proeessing, Kobe,1999,pp:109-113.
[35]P. F. C. de Rivaz, N. G. Kingsbury. Bayesian image deconvolution and denoising using complex wavelets. in Proc. IEEE Int. Conf. Image Processing, Thessaloniki, 2001,pp:273-276.
[36]N. G. Kingsbury,"A dual-tree complex wavelet transform with improved orthogonality and symmetry properties," in Proc. IEEE Int. Conf. Image Processing,2000,pp:375-378.
[37]N. G. Kingsbury.Design of q-shift complex wavelets for image processing using frequency domain energy minimization. In Proc. IEEE Int. Conf. Image Processing, 2003,pp:1013-1016.
[38]P. Loo, N. G. Kingsbury. Digital water marking using complex wavelets. In Proc. IEEE Int. Conf. Image Processing,2000,pp:29-32.
[39]M. Miller, N. Kingsbury, R. Hobbs. Seismic imaging using complex wavelets. In Proc. ICASSP,2005,pp:57-560.
[40]焦李成,谭山.图像的多尺度几何分析：回顾和展望[J].电子学报.2003,31(12A)
[41]E L Pennec, S Mallat. Image compression with geometrical wavelets [A].In Proc. of ICIP' 2000[C].Vancouver, Canada. September.661-664.
[42]E J Candes. Ridgelets:Theory and Applications [D]. USA:Department of Statistics, Stanford University,1998.
[43]E J Candes. Monoseale Ridgelets for the Representation of Images with Edges [R].USA: Department of Statistics, Stanford University,1999.
[44]Candes E J, D L Donoho. Curvelets [R]. USA:Department of Statistics, Stanford University, 1999.
[45]M N Do, M Vetterli. Contourlets[A]. J Stoeckler, GV Welland. Beyond Wavelets[C].Academic Press,2002.
[46]M N Do, M. Vetterli. Pyramida Directional Filter banks and curvelets [A].IEEE Conference on Image Processing, hessaloniki, Greece, October 2001.
[47]C.K.CHUI, P.MONK, L.WUYTACK, BEYOND WAVELETS, ACADEMIC PRESS, 2003,pp:83-104.
[48]P. J. Burt, E. H. Adelson. Laplacian Pyramid as a compact image code. IEEE transactions on communications,1983, pp:532-540
[49]R.H.Bamberger, M.J.T.Smith, A filer bank for the directional decomposition of images, Theory and design, IEEE Trans. Signal Proc,1992, pp:882-893.
[50]M. N. Do. Directional multiresolution image representations [D]. Ph. D. dissertation, Swiss Federal Institute of Technology, Lausance,2001.
[51]黄传波,邵杰,万鸣华,金忠Contourlet变换在图像检索中的应用[J].计算机工程与应用,2009,45(3).
[52]NG Kingsbury. The dual-tree complex wavelet transform:A new technique for shift invariance and directional filters[C].IEEE Digital Signal Processing Workshop,1998.
[53]刘波.交通标志识别及其算法研究[硕士论文].长沙：中南大学.2010.
[2]Hu S H, Huang C L. Road Sign Detection and Recognition Using Matching Pursuit Method [J]. Image and Vision Computing,2001,19(3):120-129.
[3]邵桂珠.道路交通标志识别算法的研究[硕士论文].吉林：吉林大学.2008.
[4]M. de, Saint Blancard. Road sign recognition:A study of vision-based decision making for road environment recognition[J]. Vision-based Vehicle Guidance, Springer Series in Perception Engineering,1992,pp:162-172..
[5]N. Kehtarnavaz, N. C. Griswold, D. S. Kang. Stop-sign recognition based on color shape processing. Machine Vision and Applications,1993,pp:206-208.
[6]L. Priese, J. Klieber, R. Lakmann, V. Rehrmann, R. Schian. New results on traffic sign recognition. In IEEE Proc. Intelligent Vehicle'94 Symposium,1994,pp:249-253.
[7]Jun Miura, Tsuyoshi Kanda, Yoshiaki shirai. An Active Vision System for Real-Time Traffic Sign Recognition.Proe.2000 IEEE Int. Conf. On Intelligent Transportation Systems, Dearbom, ML. USA,2000,pp:52-57.
[8]Henry X. Liu, Bin Ran. Vision-Based Stop Sign Detection and Recognition System for Intelligent Vehicles [J]. Transportation Research Record,2001,1748:161-166.
[9]Jun Miura, Tsuyoshi Kanda, Yoshiaki Shirai. An Active Vision System for Read Time Traffic Sign Recognition.Proc.2000 IEEE Int. Conf. On Intelligent Transportation Systems,2000:52-57.
[10]蒋刚毅,郑义.形态骨架匹配算法及其在交通标志识别中的应用[J].电路与系统学报,1996,1(3)：16-23.
[11]朱双东,张懿,陆晓峰.三角形交通标志的智能检测方法[J].中国图像图形学报,2006,11(8)：161-166.
[12]朱双东,刘兰兰,陆晓峰.一种用于道路交通标志识别的颜色-几何模型[J].仪器仪表学报,2007,28(5)：956-960.
[13]姚敏.数字图像处理[M],北京：机械工业出版社,2006,122-224.
[14]Shadeed, etal. Road traffic sign detection in color images. Electronics, Circuits and Systems, 2003.ICECS2003.Proeeedings of the 2003 Iota IEEE International Conference on,2003,pp:890-893.
[15]王萍,程号,罗颖听.基于色调不变的彩色图像增强[J].中国图像图形学报,2007,12(7)：1173-1178.
[16]Rafael C. Gonzalez, Richard E. Woods. Digital Image processing (Second Edition)[M]. Publishing House of Electronics Industry.2008,pp:235-236.
[17]C.冈萨雷斯,阮秋琦,阮宁智等译.数字图像处理[M].北京：电子工业出版社,2003,pp：91-112.
[18]Mean shift:a robust approach toward feature space analysis, D Comaniciu, P Meer Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol.24, No.5.2002, pp.603-619.
[19]D.Comaniciu, V. Ramesh, and P. Meer, "Real-Time Tracking of Non-Rigid Objecets Using Mean Shift," Proc.2000 IEEE Conf. Computer Vision and Pattern Recognition, vol. II, 2000,pp:142-149.
[20]朱胜利Mean Shift及相关算法在视频跟踪中的研究[博士学位论文].杭州：浙江大学,2006.
[21]张娟.基于彩色图像分割的立体匹配算法研究.[硕士论文],山东大学,2007.
[22]胡小锋,赵辉Visual C++/MATLAB图像处理与识别[M].北京：人民邮电出版社.2004.
[23]Rodrigues, M. A. Liu, Y. Motion Parameter Constraints Analysis from a Single Image. International Conference of IEEE on Image Processing,1999, pp:704-708.
[24]Jacinto Nascimento,Arnaldo,J.Abrantes,Jorge S.Marques.Using Middle Level Features for Robust Shape Tracking.Pattern Recognition Letters,2003,pp:295-307
[25]D. Gabor, "Theory of communication," IEEE Trans. Information Theory, Vol.9, No.3, 1946,pp.76-87.
[26]Mohammad A. Tinati, Behzad Mozaffary, "Comparison of the wavelet and short time Fourier transforms for spectral analysis of speech signals," in Proc. the 5th WSEAS,2005,pp.31-35.
[27]Abdul-Rahman A, Hailes S.A Distributed Trust Model[C].In the Proceeding of the 1997 New Security Paradigms Workshop, Cumbria, UK:ACM Press,1998,pp:48-60.
[28]王卫卫,杨波,宋国乡.图像可靠性鉴定的数字水印算法[J].西安：西安电子科技大学学报,2001,28(4)：507-511.
[29]N G Kingsbury. The dual-tree complex wavelet transform:a new efficient tool for image restoration and enhancement, Proc. European Signal Processing Conference, EUSIPCO 98, Rhodes,1998, pp:319-322.
[30]J F A Magarey, N G Kingsbury. Motion estimation using a complex-valued wavelet transform, IEEE Trans, on Signal Processing,1998,pp:1069-84
[31]N. Kingsbury. Image processing with complex wavelets, Phil. Tran. R. Soc. Lond. A, 1999,pp:2543-2560
[32]N. Kingsbury, Complex wavelets for shift invariant analysis and filtering of signals, Appli.Comput.Harmon.Anal.,2001,pp:234-253
[33]H. Choi, J. Romberg, R. G. Baraniuk, N. Kingsbury. "Hidden Markov tree modeling of complex wavelet transforms," in Proc. ICASSP,2000,pp:133-136.
[34]P. F. C. de Rivaz, N. G. Kingsbury, "Complex wavelet features for fast texture image retrieval," in Proc. IEEE Int. Conf. Image Proeessing, Kobe,1999,pp:109-113.
[35]P. F. C. de Rivaz, N. G. Kingsbury. Bayesian image deconvolution and denoising using complex wavelets. in Proc. IEEE Int. Conf. Image Processing, Thessaloniki, 2001,pp:273-276.
[36]N. G. Kingsbury,"A dual-tree complex wavelet transform with improved orthogonality and symmetry properties," in Proc. IEEE Int. Conf. Image Processing,2000,pp:375-378.
[37]N. G. Kingsbury.Design of q-shift complex wavelets for image processing using frequency domain energy minimization. In Proc. IEEE Int. Conf. Image Processing, 2003,pp:1013-1016.
[38]P. Loo, N. G. Kingsbury. Digital water marking using complex wavelets. In Proc. IEEE Int. Conf. Image Processing,2000,pp:29-32.
[39]M. Miller, N. Kingsbury, R. Hobbs. Seismic imaging using complex wavelets. In Proc. ICASSP,2005,pp:57-560.
[40]焦李成,谭山.图像的多尺度几何分析：回顾和展望[J].电子学报.2003,31(12A)
[41]E L Pennec, S Mallat. Image compression with geometrical wavelets [A].In Proc. of ICIP' 2000[C].Vancouver, Canada. September.661-664.
[42]E J Candes. Ridgelets:Theory and Applications [D]. USA:Department of Statistics, Stanford University,1998.
[43]E J Candes. Monoseale Ridgelets for the Representation of Images with Edges [R].USA: Department of Statistics, Stanford University,1999.
[44]Candes E J, D L Donoho. Curvelets [R]. USA:Department of Statistics, Stanford University, 1999.
[45]M N Do, M Vetterli. Contourlets[A]. J Stoeckler, GV Welland. Beyond Wavelets[C].Academic Press,2002.
[46]M N Do, M. Vetterli. Pyramida Directional Filter banks and curvelets [A].IEEE Conference on Image Processing, hessaloniki, Greece, October 2001.
[47]C.K.CHUI, P.MONK, L.WUYTACK, BEYOND WAVELETS, ACADEMIC PRESS, 2003,pp:83-104.
[48]P. J. Burt, E. H. Adelson. Laplacian Pyramid as a compact image code. IEEE transactions on communications,1983, pp:532-540
[49]R.H.Bamberger, M.J.T.Smith, A filer bank for the directional decomposition of images, Theory and design, IEEE Trans. Signal Proc,1992, pp:882-893.
[50]M. N. Do. Directional multiresolution image representations [D]. Ph. D. dissertation, Swiss Federal Institute of Technology, Lausance,2001.
[51]黄传波,邵杰,万鸣华,金忠Contourlet变换在图像检索中的应用[J].计算机工程与应用,2009,45(3).
[52]NG Kingsbury. The dual-tree complex wavelet transform:A new technique for shift invariance and directional filters[C].IEEE Digital Signal Processing Workshop,1998.
[53]刘波.交通标志识别及其算法研究[硕士论文].长沙：中南大学.2010.