无人机航空遥感图像动态拼接技术的研究
|
摘要
无人机航空遥感系统具有图像分辨率高、图像实时传输、高危地区作业、成本低、机动灵活等优点,适用于低空高分辨率遥感数据的实时获取,在区域性、工程性、灾害性和军事性的遥感监测中发挥着大型遥感系统难以替代的作用。无人机执行遥感监测任务中,需要将所获取的图像以及状态数据实时传输,要求无人机航空遥感系统具备自动、高速地完成图像的获取、压缩、传输、处理、显示以及存储等功能。其中,遥感图像处理的精准性、实时性与可视性是无人机能否得以有效利用的重要前提条件。由于现有成像设备的性能所限,目前的航空遥感成像系统无法获得大面积、高分辨率的观测图像,因此需要将获取的序列遥感图像实现在线动态拼接,以提高遥感图像的信息获取能力。本文结合无人机航空遥感具体应用需求,针对航空遥感图像拼接技术进行了以下研究工作：
(1)根据无人机遥感图像成像的内、外方位元素,采用直角空间变换及二次线性插补方法,实现了遥感图像校正。根据所获取的无人机飞行状态参数,实现了连续两幅无人机航空遥感快视图像之间重叠区域的图像范围计算。
(2)提出一种分布存储环境下的并行几何校正算法,每个处理器通过计算本地输入子图像在目标图像中的范围,确定其需要进行重采样计算的区域,使计算过程中所需的数据均为本地数据,很好地解决了数据局部性问题.利用首尾相连的闭线段近似表示理想的输出图像块边界,详细讨论了局部输出区域的计算方法,并采用一种新的存储结构用于保存校正后的输出图像块信息。
(3)基于图像数据总体分布的统计,分析了飞行试验图像的成像质量。基于人眼亮度视觉特性曲线,结合小波变换和Curvelet变换特点,提出一种新的图像增强方法,实现了无人机遥感序列图像的自适应增强处理。
(4)匹配特征提取方法,提出了一种将小波多分辨率分析特性和Canny算法相结合的检测图像大边缘的方法,能够比较好的从图像中提取出比较完整的大边缘,而忽略一些小的边缘。该边缘提取方法为图像配准提供一个良好的匹配特征。
(5)将图像匹配分为粗匹配和精匹配两个步骤。粗匹配计算中,首先确定待拼接的两幅图像之间的大致重叠区域,利用小波变换与Canny算法提取图像边缘。采用区域匹配方法求得两幅图像的匹配点。精匹配计算中,在更小的搜索区域,利用最小二乘法法,计算得到待拼接图像之间的最佳相对位置关系。根据匹配结果,实现两幅图像的拼接。
(6)基于人眼的颜色视觉特性分析,提出了一种具有抗亮度干扰能力的彩色图像色差度量方法。利用颜色相似性分析,并引入协方差矩阵计算,给出了彩色图像特征模板的提取方法。利用最小二乘法,建立了两幅彩色图像之间的亮度变换函数曲线,实现了基于基准图像亮度分布的伽马校正。对文中所提出的遥感图像处理算法,实现了仿真程序设计,验证了算法的可行性,完成了无人机航空遥感图像动态拼接软件设计工作。
The Unmanned Aerial Vehicle (UAV) Aerial Remote Sensing (ARS) system has the advantages of high image resolution, real-time image transmission, operation in high-risk regions, low cost, mobility and flexibility, etc. UAVARS system is suitable for the real-time acquisition of high-resolution RS data at low altitude and plays a role which is irreplaceable by large-scale RS system in territorial, constructional, catastrophic and military RS monitoring. When carrying out missions of RS monitoring, UAV needs to transmit by real-time the obtained images and status data, therefore the functions of automatic and rapid acquisition, compression, transmission, processing, display and storage are required of the ARS system. Among those functions, accuracy, real-time performance and visibility of the RS image processing are important preconditions of the effective utilization of the UAV. Due to the limited performance of the existing imaging devices, the existing ARS imaging system cannot obtain observed images of large area or high resolution, and the system needs to dynamically splice the obtained sequence RS images on line to improve the information-obtained capability of the RS images. Based on the specific requirements for the application of the aerial UAVRS, this paper did the following researches on ARS image-splicing technology:
(1) According to the interior and exterior position elements of the imaging of the UAV RS images, right angled spatial transformation and method of quadratic linear interpolation are used to correct the RS images. According to the obtained flight-status parameters of the UAV, it is calculated the range of the overlapped-area image of two ARS quick-images taken continuously by the UAV.
(2) A parallel geometrical correction algorithm was provided based on distributed memory systems. In the algorithm, each processor calculates the corresponding area in the target image for the local sub input image, and does resampling for this area. This makes all of data needed be in local memory and no communication happens during parallel computing. Closed line segments connected end to end with each other are used to represent the ideal edge of each sub output image approximately when calculating local output area and a data structure is put forward to save irregular sub output images.
(3) Based on the visual characteristics curve of human-eye brightness, Combine the characteristics of Wavelet and Curvelet, the self-adaptive enhanced processing of the UAV ARS quick-images are realized.
(4) A new edge detector is proposed. Combined Wavelet and Canny detector, it can preserve the large-scale edges and ignore the sharp textures. It is suit for image registration.
(5) Image matching includes two procedures, i.e. rough matching and fine matching. In rough matching, the area coverage of overlapped regions between two consecutive images to be stitched is determined approximately at first. Both of the overlapped regions of the two images are processed by wavelet transform and Canny Operator, and then the edge of the images has been extracted. Obtained the match point used regional matching method. In the fine matching, the sequential similarity detection algorithm (SSDA) is adopted to perform matching computation in the some small regions near the positions got in the rough matching, and then the relative position offsets in X-orientation and Y-orientation between the two consecutive images are got. Based on the result of the image matching, the two images are stitched.
(6) Based on the analysis of human-eye color vision characteristics, an anti-brightness-disturbance color difference measuring method for color images is put forward. By using analysis of color similarity and introducing covariance matrix calculation, a method for extracting the characteristics template of color images is given. By using least square method, it is established the function curve of brightness transformation between two color images, and the gamma correction is realized based on the reference image brightness-distribution. On the RS image processing algorithm put forward by this paper, the simulating programming is realized, the feasibility of the algorithm is verified, and the design of the dynamic splicing software for UAVARS images is accomplished.
(1)根据无人机遥感图像成像的内、外方位元素,采用直角空间变换及二次线性插补方法,实现了遥感图像校正。根据所获取的无人机飞行状态参数,实现了连续两幅无人机航空遥感快视图像之间重叠区域的图像范围计算。
(2)提出一种分布存储环境下的并行几何校正算法,每个处理器通过计算本地输入子图像在目标图像中的范围,确定其需要进行重采样计算的区域,使计算过程中所需的数据均为本地数据,很好地解决了数据局部性问题.利用首尾相连的闭线段近似表示理想的输出图像块边界,详细讨论了局部输出区域的计算方法,并采用一种新的存储结构用于保存校正后的输出图像块信息。
(3)基于图像数据总体分布的统计,分析了飞行试验图像的成像质量。基于人眼亮度视觉特性曲线,结合小波变换和Curvelet变换特点,提出一种新的图像增强方法,实现了无人机遥感序列图像的自适应增强处理。
(4)匹配特征提取方法,提出了一种将小波多分辨率分析特性和Canny算法相结合的检测图像大边缘的方法,能够比较好的从图像中提取出比较完整的大边缘,而忽略一些小的边缘。该边缘提取方法为图像配准提供一个良好的匹配特征。
(5)将图像匹配分为粗匹配和精匹配两个步骤。粗匹配计算中,首先确定待拼接的两幅图像之间的大致重叠区域,利用小波变换与Canny算法提取图像边缘。采用区域匹配方法求得两幅图像的匹配点。精匹配计算中,在更小的搜索区域,利用最小二乘法法,计算得到待拼接图像之间的最佳相对位置关系。根据匹配结果,实现两幅图像的拼接。
(6)基于人眼的颜色视觉特性分析,提出了一种具有抗亮度干扰能力的彩色图像色差度量方法。利用颜色相似性分析,并引入协方差矩阵计算,给出了彩色图像特征模板的提取方法。利用最小二乘法,建立了两幅彩色图像之间的亮度变换函数曲线,实现了基于基准图像亮度分布的伽马校正。对文中所提出的遥感图像处理算法,实现了仿真程序设计,验证了算法的可行性,完成了无人机航空遥感图像动态拼接软件设计工作。
The Unmanned Aerial Vehicle (UAV) Aerial Remote Sensing (ARS) system has the advantages of high image resolution, real-time image transmission, operation in high-risk regions, low cost, mobility and flexibility, etc. UAVARS system is suitable for the real-time acquisition of high-resolution RS data at low altitude and plays a role which is irreplaceable by large-scale RS system in territorial, constructional, catastrophic and military RS monitoring. When carrying out missions of RS monitoring, UAV needs to transmit by real-time the obtained images and status data, therefore the functions of automatic and rapid acquisition, compression, transmission, processing, display and storage are required of the ARS system. Among those functions, accuracy, real-time performance and visibility of the RS image processing are important preconditions of the effective utilization of the UAV. Due to the limited performance of the existing imaging devices, the existing ARS imaging system cannot obtain observed images of large area or high resolution, and the system needs to dynamically splice the obtained sequence RS images on line to improve the information-obtained capability of the RS images. Based on the specific requirements for the application of the aerial UAVRS, this paper did the following researches on ARS image-splicing technology:
(1) According to the interior and exterior position elements of the imaging of the UAV RS images, right angled spatial transformation and method of quadratic linear interpolation are used to correct the RS images. According to the obtained flight-status parameters of the UAV, it is calculated the range of the overlapped-area image of two ARS quick-images taken continuously by the UAV.
(2) A parallel geometrical correction algorithm was provided based on distributed memory systems. In the algorithm, each processor calculates the corresponding area in the target image for the local sub input image, and does resampling for this area. This makes all of data needed be in local memory and no communication happens during parallel computing. Closed line segments connected end to end with each other are used to represent the ideal edge of each sub output image approximately when calculating local output area and a data structure is put forward to save irregular sub output images.
(3) Based on the visual characteristics curve of human-eye brightness, Combine the characteristics of Wavelet and Curvelet, the self-adaptive enhanced processing of the UAV ARS quick-images are realized.
(4) A new edge detector is proposed. Combined Wavelet and Canny detector, it can preserve the large-scale edges and ignore the sharp textures. It is suit for image registration.
(5) Image matching includes two procedures, i.e. rough matching and fine matching. In rough matching, the area coverage of overlapped regions between two consecutive images to be stitched is determined approximately at first. Both of the overlapped regions of the two images are processed by wavelet transform and Canny Operator, and then the edge of the images has been extracted. Obtained the match point used regional matching method. In the fine matching, the sequential similarity detection algorithm (SSDA) is adopted to perform matching computation in the some small regions near the positions got in the rough matching, and then the relative position offsets in X-orientation and Y-orientation between the two consecutive images are got. Based on the result of the image matching, the two images are stitched.
(6) Based on the analysis of human-eye color vision characteristics, an anti-brightness-disturbance color difference measuring method for color images is put forward. By using analysis of color similarity and introducing covariance matrix calculation, a method for extracting the characteristics template of color images is given. By using least square method, it is established the function curve of brightness transformation between two color images, and the gamma correction is realized based on the reference image brightness-distribution. On the RS image processing algorithm put forward by this paper, the simulating programming is realized, the feasibility of the algorithm is verified, and the design of the dynamic splicing software for UAVARS images is accomplished.
引文
[1]钟力,胡晓峰.重叠图像拼接算法[J].中国图像图形学报,1998,3(5)：367-370.
[2]谢凤英,姜志国.基于互相关的显微医学图像配准[J].中国体视学与图像分析,2001,6(3)：175-178.
[3]殷世民,刘上乾,吴志鹏等.一种基于特征区域分割的图像拼接算法[J].西安电子科技大学学报,2002,29(6)：768-771.
[4]Kim D H,Yoon Y I,Choi J S. An Efficient Method to Build Panoramic Image Mosaics [J]. Pattern Recognition Letters,2003,24(14):2421-2429.
[5]王建忠,肖绍良.图像镶嵌及其边界处理[J].模式识别与人工智能,1993,6(3)：189-195.
[6]徐正光,田清,张利欣.图像拼接方法探讨[J].微计算机信息,2006,22(10)：255-257.
[7]李从利,韩裕生,冷晓艳,薛模根.序列图像拼接过程中误匹配的消除[J].计算机应用与软件,2006,23(11)：93-97.
[8]朱述龙,钱曾波.遥感图像镶嵌时拼接缝的消除方法[J].遥感学报,2002,6(3)：183-187.
[9]曹清.大型图像数据库中的色调调整方法[J].武汉大学学报(信息科学),2003,18(3)：311-314.
[10]杜志军,贾平.灰度投影在块匹配算法中的应用[J].微计算机信息,2007,23(2)：269-272
[11]徐玮,张茂军,吴玲达.虚拟实景空间的颜色校正方法研究[J].小型微型计算机系统,2001,22(2)：165-167.
[12]葛仕明,程义民,曾丹,李杰.基于梯度场整体变分模型的无缝图像处理方法[J].中国科学院研究生院学报,2006,23(5)：665-669.
[13]赵卿松.序列图像拼接中的交互调整方法[J],计算机工程,2007,33(4).201-203.
[14]周廷刚.遥感彩色图像镶嵌拼接缝的消除方法研究[J].计算机工程与应用,2004,36：84-86.
[15]沈项军,李峰,陈金华.一种基于特征跟踪的彩色序列图像拼接方法[J].微型电脑应用,2003,19(3)：39-41.
[16]严大勤,孙鑫.一种基于区域匹配的图像拼接算法[J],仪器仪表学报,2006,27(6)：749-753.
[17]高富强,张帆.一种快速彩色图像匹配算法[J].计算机应用,2005,25(11)： 2604-2605+2611.
[18]冷晓艳.空中侦察图像连续拼接中的平滑算法研究[J].计算机工程与科学,2007,29(2)：52-55.
[19]王伟,陆佩忠.数字图像拼接技术[J].小型微型计算机系统,2006,27(7)：1347-1352.
[20]李胜睿,李翠华.基于梯度滤波的彩色图像快速拼接与实现技术[J].厦门大学学报(自然科学版),2003,43(1)：29-34.
[21]王平江,甄恒洲.特征稀少图像的拼接方法[J].华中科技大学学报(自然科学版)2006,34(8)：13-16.
[22]赵晓敏.一种基于图像投影特征的射线图像拼接方法[J],光学技术,2006,32(6)：929-934.
[23]Hisausw, CIE Industrial color difference evaluation [M]. Vienna:CIE Publication, 1995.
[24]Berns R S, Alman D H, Reniff L et al. Visual determination of supra threshold color difference tolerances using profit analysis [J]. Color Research and Application,1991, 16(5):297-299.
[25]Levkowitz H, Herman G T. Color scales for image data [J]. IEEE Computer Graphics and Application,2006,12(1):72-75.
[26]Cyheuew,G. Studio encoding parameters of digital television for standard 4:3 and wide-screen 16:9 aspect ratios [M]. Geneva:ITU-R, Recommendation BT.601-5, 1994.
[27]Ohta Y, Kanade T, Sakai T. Color information for region segmentation [J]. Computer Graphics and Image Processing,1980,13(2):222.
[28]Pratt W K. Digital image processing (2nd Ed.) [M]. New York:John Wiley,1991.
[29]Foley J D, van Dam A. Fundamentals of Interactive Computer Graphics [M]. MA: Addison-Wesley,1982.
[30]Ledley S, Buas M, Golab T. Fundamentals of true-color image processing [C], Proceedings of 10th International Conference on Pattern Recognition. Atlantic City, 1990,791-795.
[31]Gonzalez R C, Woods R E. Digital image processing (3rd Ed.) [M]. Reading, MA: Addison Wesley,1992.
[32]Bajon J, Cattoen M, Kim S D. Real-time colorimetric transformations used in robot vision [C]. Proceedings of MICAD, French,1985,76-86.
[33]Machuca R, Phillips K. Application of vector fields to image processing [J]. IEEE Trans PAMI,1983,5:316-329.
[34]Pitas I, Venetsanopoulos A N. Nonlinear digital filters principles and applications [M]. New York:Kluwer Academic Publishers,1990,129-138.
[35]Astola J, Haavisto P, Neuvo Y. Vector median filter [C]. Proc. of IEEE Int. Conf. on Image Processing,1990,78:678-689.
[36]Trahanias P E,Venetsanopoulos A N. Vector directional filters proposed class of multichannel image processing filters [J]. IEEE Trans of Image Processing,1993,2: 528-534.
[37]Karakos D G, Tranias P E. Combining vector median and vector directional filters: the directional-distance filters [C]. Proc of IEEE Int. Conf on Image Processing 95, 1995,1:171-174.
[38]Plataniotis K N, Androutsos D, Venetsanopoulos A N. Content-based color image filters [J]. Electronics Letters,1997,33:203-212.
[39]Buchowicz A, Pitas I. Multidimensional distance filters [C]. Proc of IEEE Int Conf on Image Processing 94,1994,2:575-579.
[40]郁伯康,郁梅.彩色图像滤波的新方法[J].电子科技大学学报,1999,28(1)：14-19.
[41]Ralph Sucher, A recursive nonlinear filter for removal of impulse noise [J]. Proc. of the IEEE Int. Conf. on Image Processing (ICIP'95),1995,183-186.
[42]蒋刚毅,郁梅,郁伯康.自适应彩色图像滤波新方法[J].科学通报,1999,9：1937-1942.
[43]李永峰,丁润涛,国澄明.一种彩色图像滤波的改进矢量中值算法[J].数据采集与处理.2003,18(3)：361-364.
[44]郁梅,郁伯康,蒋刚毅,郑义.基于噪声检测的彩色图像脉冲噪声滤波[J].计算机工程与应用,2000,3：55-57.
[45]王文惠,楼生强,万建伟,周良柱.一种彩色图像的非线性自适应滤波算法[J].计算机工程与科学,2001,23(4)：18-20.
[46]郁伯康,郁梅.彩色图像脉冲噪声的自适应矢量滤波[J].电子科技大学学报,2000,29(2)：131-135.
[47]章毓晋.图像分割[M].北京：科学出版社,2001.
[48]Pal N R, Pal S K. A review on image segmentation techniques [J]. Pattern Recognition,1993,26:1277-1294.
[49]Uchiyama T, Arbib M A. colour image segmentation using competitive learning [J]. IEEE-PAMI,1994,16:1197-1206.
[50]Lim Y W, Lee S U. On the color image segmentation using algorithm based on the thresholding and fuzzy C-means techniques [J]. Pattern Recognition,1990,23(9): 935-952.
[51]柏子游,张勇,虞烈.一种彩色图像的色彩分割方法[J].模式识别与人工智能,1999,12(2)：241-244.
[52]郭国栋,马颂德.彩色图像分割[J].中国图像图形学报,1998,3(11)：918-921.
[53]Ohlander R, Price K, Reddy D R. Picture segmentation using a recursive region splitting method [J]. CGIP,1978,8(3):313-333.
[54]Tremeau A, Borel N. A region growing and merging algorithm to color segmentation [J]. Pattern Recognition,1997,30(7):1191-1203.
[55]范立南.基于多结构元形态边缘检测与不变矩特征模式识别研究[D].沈阳：东北大学,2004.
[56]Kass M, Witkin A, Terzopoulos D. Snakes:active contour models [C]. Int.J.Computer Vision,1987,321-331.
[57]刘少创,林宗坚.彩色航空影象分割的OCTOPUS方法[J].中国图像图形学报,1997,2(11)：790-794.
[58]粟海华,王睿斌,庄镇泉.一种基于判决神经网络的彩色图像分色算法[J].模式识别与人工智能,1999,12(3)：345-358.
[59]N Ikonomakis, K N Plataniotis, and A N Ventsanopoulos. Grey-scale and colour image segmentation via region growing and region merging [J]. Canadian Journal of Electrical and Computer Engineering,1998,28-1(1):43-47.
[60]孟章荣.各种颜色模型选用需求分析[J].中国图像图形学报,1996,1(3)：238-241.
[61]Shafarenko L, Petrou M, Kittler J. Histogram-based segmentation in a perceptually uniform color space [J]. IEEE Trans on Image Processing,1998,7(9):1354-1358.
[62]Tominaga S. A color classification method for color image using a uniform color space [C]. Proceeding of the 10th Int. Conf. on Pattern,1990,274-280.
[63]Vlachos T, Constantinides A G. A graph-theoretic approach to color image segmentation and contour classification [C]. The 4th Int. Conf. on Image Processing and its Application,1992,354-362.
[64]Samet H. The quad tree and related hierarchical data structures [J]. Computer Surveys,1984,16(2):187-230.
[65]Gevers T, Kajcovski V K. Image segmentation by directed region subdivision [C]. Proceeding of the 12th IAPR Int. Conf. on Pattern Recognition,1994,963-972.
[66]Loncaric S. A survey of shape analysis techniques [J]. Pattern Recognition,1998, 31(8):983-1010.
[67]席砺莼,闫宏伟.彩色图像的分割技术[J].微机发展,2003,13(4)：46-48.
[68]Healey G E. Segmenting image using normalized color [J]. IEEE Trans on System, Man, and Cybernetics,1992,22:64-73.
[69]Klinker G J, Shafer S A, Kanada T. A physical approach to color image understanding [J]. International Journal of Computer Vision,1990,4(1):7-38.
[70]Saber E, Tekalp A M, Bozdagi G. Fusion of color and edge information for improved segmentation and edge linking [J]. Image and Vision Computing,1997,15:769-780.
[71]Lim Y W, Lee S U. On the color image segmentation algorithm based on the threshold and the fuzzy c-means techniques [J]. Pattern Recognition,1990,23(9): 935-952.
[72]Celenk M. A color technique for image segmentation [J]. Computer Vision, Graphics, and Image processing,1990,52(1):145-170.
[73]Vailaya A, Jain A, Zhang H J. On image classification:city images vs. landscapes [J]. Pattern Recognition,1998,31(12):1921-1935.
[74]Yu H F, Zen H, Wang R L. Color spaces conversion of image between the input and output devices by means of artificial neural network [C]. Proc.1ICIG,2000:50-53.
[75]Zhang G P. Neural networks for classification:a survey [J]. IEEE Trans. on Systems, Man, and Cybernetic-Part C,2000,30(4):451-462.
[76]Gonzalez R C, Woods R E. Digital Image Processing [M].3rd ed. Addison-Wesley, 1992.
[77]Serra J. Image analysis and Mathematical Morphology [M]. London:Academic Press, 1982.
[78]崔屹.图像处理与分析数学形态学方法及应用[M].北京：科学出版社,2000.
[79]龚炜,石青云.数字空间中的数学形态学理论与应用[M].北京：科学出版社,1997.
[80]杨述斌,彭复员.数学形态学在图像处理中的应用与发展[J].武汉化工学院学报,2004,26(1)：70-73.
[81]吴敏金.图像形态学[M].上海：上海科技文献出版社,1991.
[82]Heath M, Sarkar S, Sanoki T. Comparison of edge detector:a morphology and initial study [J]. Computer Vision and Image Understanding,1998,69(1):38-54.
[83]Parker J R. Special issue on mathematical morphology and nonlinear image processing [J]. Pattern Recognition,2000,33(6):813-819.
[84]Sternberg S R. Grayscale morphology [J]. Computer Vision, Graph ics and Image P processing,1986,35(1):333-355.
[85]Comer M L, Delp E J. An empirical study of morphological operators in color image enhancement [C]. In Proc the SPIE Conference on Image Processing Algorithms and Techniques III San Jose [A]. California,1992,314-325.
[86]黄樟灿,陆昊娟.彩色图象去噪方法探讨[J].计算机工程与科学,2001,23(4)：15-17.
[87]蒋刚毅,郑义.关于彩色图象处理的形态学算子研究[J].中国图象图形学报,2000,5A(4)：293-299.
[88]Vision J, Sinha D, Douherty E R. Fuzzy mathematical morphology [J]. Communication and Imagine and Representation,1992,3 (3):286-302.
[89]周煦潼,施鹏飞.模糊数学形态学理论与应用[M].上海：上海交通大学出版社,1998.
[90]Koskinen L, A stola J, Neuvo Y. Soft morphological filters [A]. Proc. SPIE Int. Society of Optical Engineering [C].1991,15 (6):262-270.
[91]Frank Y Analysis of the properties of soft-morphological filtering using threshold decomposition [J]. IEEE Trans. On Signal Proessing,1995,43 (2):539-544.
[92]舒昌献,莫玉龙.基于软形态学的边缘检测[J].中国图象图形学报,1999,4A(2)139-142.
[93]Gasteratos A, Tsalides S. Fuzzy soft mathematical morphology [J]. Image Signal processing,1998,145 (1):41-49.
[94]戴青云,余英林.一种基于小波与形态学的车牌图象分割方法[J].中国图象图形学报,2000,5A(5)：411-415.
[95]孙杰,张铁群,翟宏琛,唐亦亮.彩色目标识别中的单通道目标分割方法[J].南开大学学报(自然科学),2002,35(1)：83-87.
[96]Deutsch M, Garcia J, Mandlovic D. Multi-chnnel signal output color pattern recognition by use of a joint transforms correlation [J]. Applied Ottics,1996,35(35): 6976-6982.
[97]Zhai Hongchen, Mu guoguang, Sun Jie et al. Color pattern recognition in white-light joint transform correlation [J]. Applied optics,1999,38(35):7238-7244.
[98]Zhai Hongchen, Zhu Xiushan, Mu Guoguang. White light JTC for color pattern recognition[C].18th congress of the international commission for optics, San Francisco, USA,1999:213-214.
[99]Munsell A H. A color notation (8th Ed.) [M]. Boston:Munsell Color Company,1939.
[100]Ohta Y, Kanade T, Sakal T. Color information for region segmentation [J]. Graphics Image Process,1980,3:241-244.
[101]Huang W C, Wu C H. Adaptive color image processing and recognition for varying backgrounds and illumination conditions [J]. IEEE Transactions on Industrial Eletronics,45(2):351-357.
[102]Moghaddamzadeh A, Bourbakis N. A fuzzy region growing approach for segmentation of color images [J]. Pattern Recognition,1997,30(6):876-881.
[103]Jong Hwan Kim, Hyun Sik Shim, Myung Jin Jung. Cooperative Multi-Agent Robotic Systems [C]:In:TheRobot2Soccer Perspective. Proceedings of the MicroRobot World Cup Soccer Tournament'97. KAIST, Tae-jon, Korea.1997,3-14.
[104]佟国峰,高大志,薛定宇,徐心和.足球机器人视觉系统的设计与开发[C].见：机器人足球研讨班论文集.沈阳：东北大学,1998,20-23.
[105]王文学,赵妹颖,孙萍,等.多智能足球机器人系统的关键技术[J].东北大学学 报,2001(4)：192-195.
[106]何超.足球机器人视觉图像的快速识别[A].席裕庚.第四届全球智能控制与自动化大会论文集[C].上海：华东理工大学出版社,2002.
[107]赵姝颖.机器人视觉子系统[J].机器人技术与应用,2000(2)：26-28.
[108]汤顺清.色度学[M].北京：北京理工大学出版社,1990.
[109]黄晶,赵臣,周明明.基于快速彩色空间变换的足球机器人目标搜索[J].哈尔滨工业大学学报,2003,35(9)：1036-1039.
[110]K S Fu. Syntactic pattern recognition and application[M]. Prentice-Hall, Englewood Cliffs, NJ,1982.
[111]P A Devijver, J Kittler. Pattern recognition:a statistical approach[M]. Prentice-Hall, Englewood Cliffs, NJ,1982.
[112]E Oja. Subspace methods of pattern recognition[M]. Research Studies Press, Letchworth, England,1983.
[113]P A Devijver, J Kittler. Pattern recognition theory and applications[M]. Springer Verlag, Berlin-New York-Tokyo,1986.
[114]G Joy, Zhigang Xiang. Reducing false contours in quantized color images[J]. Computers and Graphics,1996,20 (2):231-242.
[115]P Heckbert. Color image quantization for frame buffer display[J]. Computer Graphics,1982,16 (6):297-307.
[116]Y Linde, A Buzo, R M Gray. An algorithm for vector quantizes design [J]. IEEE Transactions on Communications,1980,28 (1):84-95.
[117]W H Equitz. A new vector quantization-clustering algorithm [J]. IEEE Transactions on Acoustics, Speech, and Signal Processing,1989,37 (10):1568-1575.
[118]Xiang Zhigang, Joy G. Color image quantization by agglomerative clustering [J]. IEEE Computer Graphics and Applications,1994,14 (1):44-48.
[119]M T Orchard, C A Bouman. Color quantization of images [J]. IEEE Transactions on Signal Processing,1991,39 (12):2677-2690.
[120]R S Gentile, J P Allebach, E Walow it. Quantization of color images based on uniform color spaces [J]. Journal of Imaging Techno logy,1990,16 (1):11-21.
[121]赵燕伟,王万良.基于聚类分析的色彩量化新算法及其应用[J].计算机辅助设计与图形学学报,2000,12(5)：340-343.
[122]刘相滨,邹北骥.一种新的颜色聚类算法及其图像检索[J].计算机工程与应用,2001.13：126-128.
[123]于晓波,孙菁,栾新.基于色度平面的自适应颜色聚类[J].青岛海洋大学学报,2002,32(6)：981-986.
[124]任智斌,隋永新,杨英慧,杨怀江.在均匀颜色空间中实现彩色图像的颜色量化[J]. 光学,2002,10(4)：340-345.
[125]童劲松,蔡青.均匀颜色空间的线性颜色表生成[J].计算机辅助工程,1995,(4)：48-55.
[126]刘友明,刘希顺,刘安之,王博亮.一种基于LUV均匀颜色空间的彩色分割方法[J].微型电脑应用,2000,16(12)：27-29.
[127]艾矫燕,朱学锋.基于改进算法的ART2网络用于微晶玻璃颜色分类[J].华南理工大学学报(自然科学版),2003,31(1)：74-78.
[128]吴颖谦,胡新荣,杨翠萍,王天珍.一种新的基于神经网络彩色图像颜色量化方法[J].武汉汽车工业大学学报,2000,22(3)：33-36+33.
[129]Wyszecki G., Stiles W.S. Color science,2nd Ed [M]. New York:John Wiley & Sons,1982.
[130]Judd D.B. Colorimetr y [M]. National bureau of standards circular 478,1950.
[131]Hunt R. W.G. The reproduction of color,3rd Ed [M]. New York:John Wiley & Sons, 1975.
[132]Hunter R.S. The measurement of apperance[M]. New York:John Wiley & Sons, 1975.
[133]Meyer G.W. Tutorial on color science [J]. The Visual Computer,1986,2:278-290.
[134]Chamberlin. Colour:its measurement, computation and application [M]. Heyden, 1980.
[135]S Zeki. Colour coding in the cerebral cortex:The reaction of cells in monkey visual cortex to wavelengths and colours [J]. Neuroscience,1983,9:741-765.
[136]Evan Thompson, Adrian Palacios, and Francisco J. Varela. Ways of coloring: Comparative color vision as a case study for cognitive science [J]. Behavioral and brain sciences,1992,15(1):1-74.
[137]D W Hamlyn. The penguin history of western philosophy [M]. Penguin,1987.
[138]刘文耀.光电图像处理[M].北京：电子工业出版社,2002.
[139]容观澳.计算机图像处理[M].北京：清华大学出版社,2000.
[140]朱正芳,汤顺青.色度学及其进展[J].物理,1996,25(6)：342-347.
[141]Robert S. and Randolph B. Perception [M]. New York, McGraw-Hill, third edition, 1994.
[142]R L Geogory. Eye and Brain,3rd Ed. [M]. London:Weidenfeld and Nicholson,1977.
[143]Elizabeth A, Martin M A. Concise Medical Dictionary,4th ED [M]. London:Oxford University Press,1994.
[144]刘津,陈奇,俞瑞钊.计算机颜色科学的发展[J].计算机工程,1997,23(2)：47-51.
[145]田玉敏,梁若莹.计算机彩色输入输出设备常用颜色空间及其转换[J].计算机工程,2002,28(9)：198-200+274.
[146]田登.色彩工学[M].西安：西安交通大学出版社,1998.
[147]李维.颜色特性变量及其交互作用分析[J].天津城市建设学院学报,2001,7(3)：204-207.
[148]刘伟奇,冯睿,周丰昆.符合人眼视觉特性的颜色亮度模型[J].光学学报,1999,19(10)：1426-1429.
[149]R O Duda, P E Hart. Pattern classification and scene analysis [M]. New York:John Wiley and Sons,1973.
[150]Gonzalez R C, Woods R E著,阮秋琦译.数字图像处理(第2版)[M].北京：电子工业出版社,2003 A.D. Gordon. Classification [M]. London:Chapman & Hall, 1981.
[151]D C Tseng, C H Chang. Color segmentation using perceptual attributes [C]. Proc. 11th Int.,1992, Conference on Pattern recognition III:Conf C 228-231.
[152]The CMC of the SDC, CMC color-difference formulae [J]. Color Res. Appl.,1984,9: 250.
[153]Clarke F J J, McDonald R, Rigg B. Modification to the JPC79 color-difference formula [J]. J Soc Dyers Color,1984,100:128-132.
[154]Alman D H. Cie TC 1-29 industrial color-difference evaluation [J]. Color Res. Appl. 1991,16:219-220.
[155]Alman D H. CIE TC 1-29.Industrial color-difference evaluation progress report [J]. Color Res. Appl.1993,18:137-139.
[156]Jan P Allebach. Processing digital color images:From capture to display [J]. Physics Today,1992,2:32-39.
[157]Robert M. Boynton. Human colour vision [M]. Holt, Rinehart and Winston,1979.
[158]Symon D O. Colour, colour spaces and the human visual system [J]. Technical report, School of Computer Science, University of Birmingham, England,1989.
[159]Mark D. Fairchild. Color appearance models [M]. Massachusetts:Addison Wesley, Reading,1998.
[160]W S Stiles, Gunter W. Color science concepts and methods, quantitative data and formula [M]. New York:John Wiley and Sons Inc.,2000.
[161]Lin H M and Willson A N. Median filters with adaptive-length. IEEE CAS1,1988, 35(6):675-690.
[162]Florencio D A F and Schafer R W. Decision-based median filter using local signal statistics. Proc. SPIE Symp Visual Comm. Image Processing, Chicago,1994,1(23): 268-275.
[163]Hardie R E and Barner K E. Rank conditioned rank selection flters for signal restoration. IEEE IP,1995,3(2):192-206.
[164]Abreu E, Lightone M and Mitra S K et al. A new efficient approach for the removal of impulse noise from highly corrupted images. IEEE IP,1996,5(6):1012-1025.
[165]Russo F. and Ramponi G. A fuzzy filter with adaptive length. IEEE CAS1,1988, 35(6):715-720.
[166]Zhang D, Wang Z. Impulse noise detection and removal using fuzzy techniques. Electronics Letters,1997,33(5):378-379.
[167]Kim V, Yaroslavskii L. Rank algorithms for picture processing. Computer Vision, Graphics, Image Processing,1986,35(2):234-258.
[168]Mitra S K, Yu T H. A new algorithm for the removal of impulse noise from highly corrupted images. Proc. IEEE CAS, London,1994,17-20.
[169]Ralph Sucher. A recursive nonlinear filter for removal of impulse noise. Proc. of the IEEE Int. Conf. On Image Processing (ICIP'95),1995,183-186.
[170]黄庆华,周荷琴,冯焕清.一种快速有效的图像脉冲噪声滤除方法[J].计算机工程与应用,2002,17(8)：113-115.
[171]李树涛,王耀南.图像椒盐噪声的非线性自适应滤除[J].中国图像图形学报,2000,5(12)：999-1001.
[172]孙即祥.模式识别中的特征提取与计算机视觉不变量[M].北京：国防工业出版社,2001.
[173]Christopher M. Neural networks for pattern recognition [M]. Oxford:Clarendon Press,1997.
[174]Cybenko G. Approximation by superpositions of a sigmoidal function [J]. Mathematics of Control, Signals, and Systems,1989,2:303-314.
[175]Hornik K M, Stinchcombe M, White H. Multi-layer feedforward networks are universal approximators [J], Neural Networks,1989,2:359-366.
[176]徐丽娜.神经网络控制[M].北京：电子工业出版社,2003.
[177]Nielsen R. Theory of the back-propagation neural networks[C]. Proc of the International Joint Conference on Neural Networks,1989,593-611.
[178]焦李成.神经网络系统理论[M].西安：西安电子科技大学出版社,1990.
[179]缪绍纲.数字图像处理[M].成都：西南交通大学出版社,2001.
[180]朱剑英.智能系统非经典数学方法[M].武汉：华中科技大学出版社,2001.
[181]王耀南,李树涛,毛建旭.计算机图像处理与识别技术[M].北京：高等教育出版社,2001.
[182]石俊生,杨卫平,白凤翔,张韬,唐伟.彩色图象分割与颜色特征选择[J].云南师范大学学报,1999,19(6)：53-56.
[183]刘忠伟,章毓晋.十种基于颜色特征的图像检索算法的比较和分析[J].信号处理,2000,16(1)：79-84.
[184]章毓晋.基于内容的视觉信息检索[M].北京：科学出版社,2003.
[185]Corridoni J M, Del Bimbo A. Film editing reconstruction and semantic analysis [C]. Proc.6ICCAIP,1995,938-943.
[186]田国会,尹建琴,宁春林等.足球机器人视觉子系统及其关键问题[J].山东工业大学学报,2002,32(1)：86-91.
[187]赵姝颖,佟国峰.微型足球机器人的设计与开发[J].机器人技术与应用,1999,1(2)：22-28.
[188]胡英,徐心和.色标设计与辨识算法研究[J].中国图像图形学报,2002,7(12)：1291-1295.
[189]阮秋琦.数字图像处理学[M].北京：电子工业出版社,2001.
[190]陈凤东,洪炳荣,朱莹.基.于HSI颜色空间的多机器人识别研究[J].哈尔滨工业大学学报,2004,36(7)：928-930.
[191]阴炳皓,赵臣,韩晓军.基于改进的HSI空间模型的目标搜索方法[J].河北工业大学学报,2003,32(1)：6-10.
[2]谢凤英,姜志国.基于互相关的显微医学图像配准[J].中国体视学与图像分析,2001,6(3)：175-178.
[3]殷世民,刘上乾,吴志鹏等.一种基于特征区域分割的图像拼接算法[J].西安电子科技大学学报,2002,29(6)：768-771.
[4]Kim D H,Yoon Y I,Choi J S. An Efficient Method to Build Panoramic Image Mosaics [J]. Pattern Recognition Letters,2003,24(14):2421-2429.
[5]王建忠,肖绍良.图像镶嵌及其边界处理[J].模式识别与人工智能,1993,6(3)：189-195.
[6]徐正光,田清,张利欣.图像拼接方法探讨[J].微计算机信息,2006,22(10)：255-257.
[7]李从利,韩裕生,冷晓艳,薛模根.序列图像拼接过程中误匹配的消除[J].计算机应用与软件,2006,23(11)：93-97.
[8]朱述龙,钱曾波.遥感图像镶嵌时拼接缝的消除方法[J].遥感学报,2002,6(3)：183-187.
[9]曹清.大型图像数据库中的色调调整方法[J].武汉大学学报(信息科学),2003,18(3)：311-314.
[10]杜志军,贾平.灰度投影在块匹配算法中的应用[J].微计算机信息,2007,23(2)：269-272
[11]徐玮,张茂军,吴玲达.虚拟实景空间的颜色校正方法研究[J].小型微型计算机系统,2001,22(2)：165-167.
[12]葛仕明,程义民,曾丹,李杰.基于梯度场整体变分模型的无缝图像处理方法[J].中国科学院研究生院学报,2006,23(5)：665-669.
[13]赵卿松.序列图像拼接中的交互调整方法[J],计算机工程,2007,33(4).201-203.
[14]周廷刚.遥感彩色图像镶嵌拼接缝的消除方法研究[J].计算机工程与应用,2004,36：84-86.
[15]沈项军,李峰,陈金华.一种基于特征跟踪的彩色序列图像拼接方法[J].微型电脑应用,2003,19(3)：39-41.
[16]严大勤,孙鑫.一种基于区域匹配的图像拼接算法[J],仪器仪表学报,2006,27(6)：749-753.
[17]高富强,张帆.一种快速彩色图像匹配算法[J].计算机应用,2005,25(11)： 2604-2605+2611.
[18]冷晓艳.空中侦察图像连续拼接中的平滑算法研究[J].计算机工程与科学,2007,29(2)：52-55.
[19]王伟,陆佩忠.数字图像拼接技术[J].小型微型计算机系统,2006,27(7)：1347-1352.
[20]李胜睿,李翠华.基于梯度滤波的彩色图像快速拼接与实现技术[J].厦门大学学报(自然科学版),2003,43(1)：29-34.
[21]王平江,甄恒洲.特征稀少图像的拼接方法[J].华中科技大学学报(自然科学版)2006,34(8)：13-16.
[22]赵晓敏.一种基于图像投影特征的射线图像拼接方法[J],光学技术,2006,32(6)：929-934.
[23]Hisausw, CIE Industrial color difference evaluation [M]. Vienna:CIE Publication, 1995.
[24]Berns R S, Alman D H, Reniff L et al. Visual determination of supra threshold color difference tolerances using profit analysis [J]. Color Research and Application,1991, 16(5):297-299.
[25]Levkowitz H, Herman G T. Color scales for image data [J]. IEEE Computer Graphics and Application,2006,12(1):72-75.
[26]Cyheuew,G. Studio encoding parameters of digital television for standard 4:3 and wide-screen 16:9 aspect ratios [M]. Geneva:ITU-R, Recommendation BT.601-5, 1994.
[27]Ohta Y, Kanade T, Sakai T. Color information for region segmentation [J]. Computer Graphics and Image Processing,1980,13(2):222.
[28]Pratt W K. Digital image processing (2nd Ed.) [M]. New York:John Wiley,1991.
[29]Foley J D, van Dam A. Fundamentals of Interactive Computer Graphics [M]. MA: Addison-Wesley,1982.
[30]Ledley S, Buas M, Golab T. Fundamentals of true-color image processing [C], Proceedings of 10th International Conference on Pattern Recognition. Atlantic City, 1990,791-795.
[31]Gonzalez R C, Woods R E. Digital image processing (3rd Ed.) [M]. Reading, MA: Addison Wesley,1992.
[32]Bajon J, Cattoen M, Kim S D. Real-time colorimetric transformations used in robot vision [C]. Proceedings of MICAD, French,1985,76-86.
[33]Machuca R, Phillips K. Application of vector fields to image processing [J]. IEEE Trans PAMI,1983,5:316-329.
[34]Pitas I, Venetsanopoulos A N. Nonlinear digital filters principles and applications [M]. New York:Kluwer Academic Publishers,1990,129-138.
[35]Astola J, Haavisto P, Neuvo Y. Vector median filter [C]. Proc. of IEEE Int. Conf. on Image Processing,1990,78:678-689.
[36]Trahanias P E,Venetsanopoulos A N. Vector directional filters proposed class of multichannel image processing filters [J]. IEEE Trans of Image Processing,1993,2: 528-534.
[37]Karakos D G, Tranias P E. Combining vector median and vector directional filters: the directional-distance filters [C]. Proc of IEEE Int. Conf on Image Processing 95, 1995,1:171-174.
[38]Plataniotis K N, Androutsos D, Venetsanopoulos A N. Content-based color image filters [J]. Electronics Letters,1997,33:203-212.
[39]Buchowicz A, Pitas I. Multidimensional distance filters [C]. Proc of IEEE Int Conf on Image Processing 94,1994,2:575-579.
[40]郁伯康,郁梅.彩色图像滤波的新方法[J].电子科技大学学报,1999,28(1)：14-19.
[41]Ralph Sucher, A recursive nonlinear filter for removal of impulse noise [J]. Proc. of the IEEE Int. Conf. on Image Processing (ICIP'95),1995,183-186.
[42]蒋刚毅,郁梅,郁伯康.自适应彩色图像滤波新方法[J].科学通报,1999,9：1937-1942.
[43]李永峰,丁润涛,国澄明.一种彩色图像滤波的改进矢量中值算法[J].数据采集与处理.2003,18(3)：361-364.
[44]郁梅,郁伯康,蒋刚毅,郑义.基于噪声检测的彩色图像脉冲噪声滤波[J].计算机工程与应用,2000,3：55-57.
[45]王文惠,楼生强,万建伟,周良柱.一种彩色图像的非线性自适应滤波算法[J].计算机工程与科学,2001,23(4)：18-20.
[46]郁伯康,郁梅.彩色图像脉冲噪声的自适应矢量滤波[J].电子科技大学学报,2000,29(2)：131-135.
[47]章毓晋.图像分割[M].北京：科学出版社,2001.
[48]Pal N R, Pal S K. A review on image segmentation techniques [J]. Pattern Recognition,1993,26:1277-1294.
[49]Uchiyama T, Arbib M A. colour image segmentation using competitive learning [J]. IEEE-PAMI,1994,16:1197-1206.
[50]Lim Y W, Lee S U. On the color image segmentation using algorithm based on the thresholding and fuzzy C-means techniques [J]. Pattern Recognition,1990,23(9): 935-952.
[51]柏子游,张勇,虞烈.一种彩色图像的色彩分割方法[J].模式识别与人工智能,1999,12(2)：241-244.
[52]郭国栋,马颂德.彩色图像分割[J].中国图像图形学报,1998,3(11)：918-921.
[53]Ohlander R, Price K, Reddy D R. Picture segmentation using a recursive region splitting method [J]. CGIP,1978,8(3):313-333.
[54]Tremeau A, Borel N. A region growing and merging algorithm to color segmentation [J]. Pattern Recognition,1997,30(7):1191-1203.
[55]范立南.基于多结构元形态边缘检测与不变矩特征模式识别研究[D].沈阳：东北大学,2004.
[56]Kass M, Witkin A, Terzopoulos D. Snakes:active contour models [C]. Int.J.Computer Vision,1987,321-331.
[57]刘少创,林宗坚.彩色航空影象分割的OCTOPUS方法[J].中国图像图形学报,1997,2(11)：790-794.
[58]粟海华,王睿斌,庄镇泉.一种基于判决神经网络的彩色图像分色算法[J].模式识别与人工智能,1999,12(3)：345-358.
[59]N Ikonomakis, K N Plataniotis, and A N Ventsanopoulos. Grey-scale and colour image segmentation via region growing and region merging [J]. Canadian Journal of Electrical and Computer Engineering,1998,28-1(1):43-47.
[60]孟章荣.各种颜色模型选用需求分析[J].中国图像图形学报,1996,1(3)：238-241.
[61]Shafarenko L, Petrou M, Kittler J. Histogram-based segmentation in a perceptually uniform color space [J]. IEEE Trans on Image Processing,1998,7(9):1354-1358.
[62]Tominaga S. A color classification method for color image using a uniform color space [C]. Proceeding of the 10th Int. Conf. on Pattern,1990,274-280.
[63]Vlachos T, Constantinides A G. A graph-theoretic approach to color image segmentation and contour classification [C]. The 4th Int. Conf. on Image Processing and its Application,1992,354-362.
[64]Samet H. The quad tree and related hierarchical data structures [J]. Computer Surveys,1984,16(2):187-230.
[65]Gevers T, Kajcovski V K. Image segmentation by directed region subdivision [C]. Proceeding of the 12th IAPR Int. Conf. on Pattern Recognition,1994,963-972.
[66]Loncaric S. A survey of shape analysis techniques [J]. Pattern Recognition,1998, 31(8):983-1010.
[67]席砺莼,闫宏伟.彩色图像的分割技术[J].微机发展,2003,13(4)：46-48.
[68]Healey G E. Segmenting image using normalized color [J]. IEEE Trans on System, Man, and Cybernetics,1992,22:64-73.
[69]Klinker G J, Shafer S A, Kanada T. A physical approach to color image understanding [J]. International Journal of Computer Vision,1990,4(1):7-38.
[70]Saber E, Tekalp A M, Bozdagi G. Fusion of color and edge information for improved segmentation and edge linking [J]. Image and Vision Computing,1997,15:769-780.
[71]Lim Y W, Lee S U. On the color image segmentation algorithm based on the threshold and the fuzzy c-means techniques [J]. Pattern Recognition,1990,23(9): 935-952.
[72]Celenk M. A color technique for image segmentation [J]. Computer Vision, Graphics, and Image processing,1990,52(1):145-170.
[73]Vailaya A, Jain A, Zhang H J. On image classification:city images vs. landscapes [J]. Pattern Recognition,1998,31(12):1921-1935.
[74]Yu H F, Zen H, Wang R L. Color spaces conversion of image between the input and output devices by means of artificial neural network [C]. Proc.1ICIG,2000:50-53.
[75]Zhang G P. Neural networks for classification:a survey [J]. IEEE Trans. on Systems, Man, and Cybernetic-Part C,2000,30(4):451-462.
[76]Gonzalez R C, Woods R E. Digital Image Processing [M].3rd ed. Addison-Wesley, 1992.
[77]Serra J. Image analysis and Mathematical Morphology [M]. London:Academic Press, 1982.
[78]崔屹.图像处理与分析数学形态学方法及应用[M].北京：科学出版社,2000.
[79]龚炜,石青云.数字空间中的数学形态学理论与应用[M].北京：科学出版社,1997.
[80]杨述斌,彭复员.数学形态学在图像处理中的应用与发展[J].武汉化工学院学报,2004,26(1)：70-73.
[81]吴敏金.图像形态学[M].上海：上海科技文献出版社,1991.
[82]Heath M, Sarkar S, Sanoki T. Comparison of edge detector:a morphology and initial study [J]. Computer Vision and Image Understanding,1998,69(1):38-54.
[83]Parker J R. Special issue on mathematical morphology and nonlinear image processing [J]. Pattern Recognition,2000,33(6):813-819.
[84]Sternberg S R. Grayscale morphology [J]. Computer Vision, Graph ics and Image P processing,1986,35(1):333-355.
[85]Comer M L, Delp E J. An empirical study of morphological operators in color image enhancement [C]. In Proc the SPIE Conference on Image Processing Algorithms and Techniques III San Jose [A]. California,1992,314-325.
[86]黄樟灿,陆昊娟.彩色图象去噪方法探讨[J].计算机工程与科学,2001,23(4)：15-17.
[87]蒋刚毅,郑义.关于彩色图象处理的形态学算子研究[J].中国图象图形学报,2000,5A(4)：293-299.
[88]Vision J, Sinha D, Douherty E R. Fuzzy mathematical morphology [J]. Communication and Imagine and Representation,1992,3 (3):286-302.
[89]周煦潼,施鹏飞.模糊数学形态学理论与应用[M].上海：上海交通大学出版社,1998.
[90]Koskinen L, A stola J, Neuvo Y. Soft morphological filters [A]. Proc. SPIE Int. Society of Optical Engineering [C].1991,15 (6):262-270.
[91]Frank Y Analysis of the properties of soft-morphological filtering using threshold decomposition [J]. IEEE Trans. On Signal Proessing,1995,43 (2):539-544.
[92]舒昌献,莫玉龙.基于软形态学的边缘检测[J].中国图象图形学报,1999,4A(2)139-142.
[93]Gasteratos A, Tsalides S. Fuzzy soft mathematical morphology [J]. Image Signal processing,1998,145 (1):41-49.
[94]戴青云,余英林.一种基于小波与形态学的车牌图象分割方法[J].中国图象图形学报,2000,5A(5)：411-415.
[95]孙杰,张铁群,翟宏琛,唐亦亮.彩色目标识别中的单通道目标分割方法[J].南开大学学报(自然科学),2002,35(1)：83-87.
[96]Deutsch M, Garcia J, Mandlovic D. Multi-chnnel signal output color pattern recognition by use of a joint transforms correlation [J]. Applied Ottics,1996,35(35): 6976-6982.
[97]Zhai Hongchen, Mu guoguang, Sun Jie et al. Color pattern recognition in white-light joint transform correlation [J]. Applied optics,1999,38(35):7238-7244.
[98]Zhai Hongchen, Zhu Xiushan, Mu Guoguang. White light JTC for color pattern recognition[C].18th congress of the international commission for optics, San Francisco, USA,1999:213-214.
[99]Munsell A H. A color notation (8th Ed.) [M]. Boston:Munsell Color Company,1939.
[100]Ohta Y, Kanade T, Sakal T. Color information for region segmentation [J]. Graphics Image Process,1980,3:241-244.
[101]Huang W C, Wu C H. Adaptive color image processing and recognition for varying backgrounds and illumination conditions [J]. IEEE Transactions on Industrial Eletronics,45(2):351-357.
[102]Moghaddamzadeh A, Bourbakis N. A fuzzy region growing approach for segmentation of color images [J]. Pattern Recognition,1997,30(6):876-881.
[103]Jong Hwan Kim, Hyun Sik Shim, Myung Jin Jung. Cooperative Multi-Agent Robotic Systems [C]:In:TheRobot2Soccer Perspective. Proceedings of the MicroRobot World Cup Soccer Tournament'97. KAIST, Tae-jon, Korea.1997,3-14.
[104]佟国峰,高大志,薛定宇,徐心和.足球机器人视觉系统的设计与开发[C].见：机器人足球研讨班论文集.沈阳：东北大学,1998,20-23.
[105]王文学,赵妹颖,孙萍,等.多智能足球机器人系统的关键技术[J].东北大学学 报,2001(4)：192-195.
[106]何超.足球机器人视觉图像的快速识别[A].席裕庚.第四届全球智能控制与自动化大会论文集[C].上海：华东理工大学出版社,2002.
[107]赵姝颖.机器人视觉子系统[J].机器人技术与应用,2000(2)：26-28.
[108]汤顺清.色度学[M].北京：北京理工大学出版社,1990.
[109]黄晶,赵臣,周明明.基于快速彩色空间变换的足球机器人目标搜索[J].哈尔滨工业大学学报,2003,35(9)：1036-1039.
[110]K S Fu. Syntactic pattern recognition and application[M]. Prentice-Hall, Englewood Cliffs, NJ,1982.
[111]P A Devijver, J Kittler. Pattern recognition:a statistical approach[M]. Prentice-Hall, Englewood Cliffs, NJ,1982.
[112]E Oja. Subspace methods of pattern recognition[M]. Research Studies Press, Letchworth, England,1983.
[113]P A Devijver, J Kittler. Pattern recognition theory and applications[M]. Springer Verlag, Berlin-New York-Tokyo,1986.
[114]G Joy, Zhigang Xiang. Reducing false contours in quantized color images[J]. Computers and Graphics,1996,20 (2):231-242.
[115]P Heckbert. Color image quantization for frame buffer display[J]. Computer Graphics,1982,16 (6):297-307.
[116]Y Linde, A Buzo, R M Gray. An algorithm for vector quantizes design [J]. IEEE Transactions on Communications,1980,28 (1):84-95.
[117]W H Equitz. A new vector quantization-clustering algorithm [J]. IEEE Transactions on Acoustics, Speech, and Signal Processing,1989,37 (10):1568-1575.
[118]Xiang Zhigang, Joy G. Color image quantization by agglomerative clustering [J]. IEEE Computer Graphics and Applications,1994,14 (1):44-48.
[119]M T Orchard, C A Bouman. Color quantization of images [J]. IEEE Transactions on Signal Processing,1991,39 (12):2677-2690.
[120]R S Gentile, J P Allebach, E Walow it. Quantization of color images based on uniform color spaces [J]. Journal of Imaging Techno logy,1990,16 (1):11-21.
[121]赵燕伟,王万良.基于聚类分析的色彩量化新算法及其应用[J].计算机辅助设计与图形学学报,2000,12(5)：340-343.
[122]刘相滨,邹北骥.一种新的颜色聚类算法及其图像检索[J].计算机工程与应用,2001.13：126-128.
[123]于晓波,孙菁,栾新.基于色度平面的自适应颜色聚类[J].青岛海洋大学学报,2002,32(6)：981-986.
[124]任智斌,隋永新,杨英慧,杨怀江.在均匀颜色空间中实现彩色图像的颜色量化[J]. 光学,2002,10(4)：340-345.
[125]童劲松,蔡青.均匀颜色空间的线性颜色表生成[J].计算机辅助工程,1995,(4)：48-55.
[126]刘友明,刘希顺,刘安之,王博亮.一种基于LUV均匀颜色空间的彩色分割方法[J].微型电脑应用,2000,16(12)：27-29.
[127]艾矫燕,朱学锋.基于改进算法的ART2网络用于微晶玻璃颜色分类[J].华南理工大学学报(自然科学版),2003,31(1)：74-78.
[128]吴颖谦,胡新荣,杨翠萍,王天珍.一种新的基于神经网络彩色图像颜色量化方法[J].武汉汽车工业大学学报,2000,22(3)：33-36+33.
[129]Wyszecki G., Stiles W.S. Color science,2nd Ed [M]. New York:John Wiley & Sons,1982.
[130]Judd D.B. Colorimetr y [M]. National bureau of standards circular 478,1950.
[131]Hunt R. W.G. The reproduction of color,3rd Ed [M]. New York:John Wiley & Sons, 1975.
[132]Hunter R.S. The measurement of apperance[M]. New York:John Wiley & Sons, 1975.
[133]Meyer G.W. Tutorial on color science [J]. The Visual Computer,1986,2:278-290.
[134]Chamberlin. Colour:its measurement, computation and application [M]. Heyden, 1980.
[135]S Zeki. Colour coding in the cerebral cortex:The reaction of cells in monkey visual cortex to wavelengths and colours [J]. Neuroscience,1983,9:741-765.
[136]Evan Thompson, Adrian Palacios, and Francisco J. Varela. Ways of coloring: Comparative color vision as a case study for cognitive science [J]. Behavioral and brain sciences,1992,15(1):1-74.
[137]D W Hamlyn. The penguin history of western philosophy [M]. Penguin,1987.
[138]刘文耀.光电图像处理[M].北京：电子工业出版社,2002.
[139]容观澳.计算机图像处理[M].北京：清华大学出版社,2000.
[140]朱正芳,汤顺青.色度学及其进展[J].物理,1996,25(6)：342-347.
[141]Robert S. and Randolph B. Perception [M]. New York, McGraw-Hill, third edition, 1994.
[142]R L Geogory. Eye and Brain,3rd Ed. [M]. London:Weidenfeld and Nicholson,1977.
[143]Elizabeth A, Martin M A. Concise Medical Dictionary,4th ED [M]. London:Oxford University Press,1994.
[144]刘津,陈奇,俞瑞钊.计算机颜色科学的发展[J].计算机工程,1997,23(2)：47-51.
[145]田玉敏,梁若莹.计算机彩色输入输出设备常用颜色空间及其转换[J].计算机工程,2002,28(9)：198-200+274.
[146]田登.色彩工学[M].西安：西安交通大学出版社,1998.
[147]李维.颜色特性变量及其交互作用分析[J].天津城市建设学院学报,2001,7(3)：204-207.
[148]刘伟奇,冯睿,周丰昆.符合人眼视觉特性的颜色亮度模型[J].光学学报,1999,19(10)：1426-1429.
[149]R O Duda, P E Hart. Pattern classification and scene analysis [M]. New York:John Wiley and Sons,1973.
[150]Gonzalez R C, Woods R E著,阮秋琦译.数字图像处理(第2版)[M].北京：电子工业出版社,2003 A.D. Gordon. Classification [M]. London:Chapman & Hall, 1981.
[151]D C Tseng, C H Chang. Color segmentation using perceptual attributes [C]. Proc. 11th Int.,1992, Conference on Pattern recognition III:Conf C 228-231.
[152]The CMC of the SDC, CMC color-difference formulae [J]. Color Res. Appl.,1984,9: 250.
[153]Clarke F J J, McDonald R, Rigg B. Modification to the JPC79 color-difference formula [J]. J Soc Dyers Color,1984,100:128-132.
[154]Alman D H. Cie TC 1-29 industrial color-difference evaluation [J]. Color Res. Appl. 1991,16:219-220.
[155]Alman D H. CIE TC 1-29.Industrial color-difference evaluation progress report [J]. Color Res. Appl.1993,18:137-139.
[156]Jan P Allebach. Processing digital color images:From capture to display [J]. Physics Today,1992,2:32-39.
[157]Robert M. Boynton. Human colour vision [M]. Holt, Rinehart and Winston,1979.
[158]Symon D O. Colour, colour spaces and the human visual system [J]. Technical report, School of Computer Science, University of Birmingham, England,1989.
[159]Mark D. Fairchild. Color appearance models [M]. Massachusetts:Addison Wesley, Reading,1998.
[160]W S Stiles, Gunter W. Color science concepts and methods, quantitative data and formula [M]. New York:John Wiley and Sons Inc.,2000.
[161]Lin H M and Willson A N. Median filters with adaptive-length. IEEE CAS1,1988, 35(6):675-690.
[162]Florencio D A F and Schafer R W. Decision-based median filter using local signal statistics. Proc. SPIE Symp Visual Comm. Image Processing, Chicago,1994,1(23): 268-275.
[163]Hardie R E and Barner K E. Rank conditioned rank selection flters for signal restoration. IEEE IP,1995,3(2):192-206.
[164]Abreu E, Lightone M and Mitra S K et al. A new efficient approach for the removal of impulse noise from highly corrupted images. IEEE IP,1996,5(6):1012-1025.
[165]Russo F. and Ramponi G. A fuzzy filter with adaptive length. IEEE CAS1,1988, 35(6):715-720.
[166]Zhang D, Wang Z. Impulse noise detection and removal using fuzzy techniques. Electronics Letters,1997,33(5):378-379.
[167]Kim V, Yaroslavskii L. Rank algorithms for picture processing. Computer Vision, Graphics, Image Processing,1986,35(2):234-258.
[168]Mitra S K, Yu T H. A new algorithm for the removal of impulse noise from highly corrupted images. Proc. IEEE CAS, London,1994,17-20.
[169]Ralph Sucher. A recursive nonlinear filter for removal of impulse noise. Proc. of the IEEE Int. Conf. On Image Processing (ICIP'95),1995,183-186.
[170]黄庆华,周荷琴,冯焕清.一种快速有效的图像脉冲噪声滤除方法[J].计算机工程与应用,2002,17(8)：113-115.
[171]李树涛,王耀南.图像椒盐噪声的非线性自适应滤除[J].中国图像图形学报,2000,5(12)：999-1001.
[172]孙即祥.模式识别中的特征提取与计算机视觉不变量[M].北京：国防工业出版社,2001.
[173]Christopher M. Neural networks for pattern recognition [M]. Oxford:Clarendon Press,1997.
[174]Cybenko G. Approximation by superpositions of a sigmoidal function [J]. Mathematics of Control, Signals, and Systems,1989,2:303-314.
[175]Hornik K M, Stinchcombe M, White H. Multi-layer feedforward networks are universal approximators [J], Neural Networks,1989,2:359-366.
[176]徐丽娜.神经网络控制[M].北京：电子工业出版社,2003.
[177]Nielsen R. Theory of the back-propagation neural networks[C]. Proc of the International Joint Conference on Neural Networks,1989,593-611.
[178]焦李成.神经网络系统理论[M].西安：西安电子科技大学出版社,1990.
[179]缪绍纲.数字图像处理[M].成都：西南交通大学出版社,2001.
[180]朱剑英.智能系统非经典数学方法[M].武汉：华中科技大学出版社,2001.
[181]王耀南,李树涛,毛建旭.计算机图像处理与识别技术[M].北京：高等教育出版社,2001.
[182]石俊生,杨卫平,白凤翔,张韬,唐伟.彩色图象分割与颜色特征选择[J].云南师范大学学报,1999,19(6)：53-56.
[183]刘忠伟,章毓晋.十种基于颜色特征的图像检索算法的比较和分析[J].信号处理,2000,16(1)：79-84.
[184]章毓晋.基于内容的视觉信息检索[M].北京：科学出版社,2003.
[185]Corridoni J M, Del Bimbo A. Film editing reconstruction and semantic analysis [C]. Proc.6ICCAIP,1995,938-943.
[186]田国会,尹建琴,宁春林等.足球机器人视觉子系统及其关键问题[J].山东工业大学学报,2002,32(1)：86-91.
[187]赵姝颖,佟国峰.微型足球机器人的设计与开发[J].机器人技术与应用,1999,1(2)：22-28.
[188]胡英,徐心和.色标设计与辨识算法研究[J].中国图像图形学报,2002,7(12)：1291-1295.
[189]阮秋琦.数字图像处理学[M].北京：电子工业出版社,2001.
[190]陈凤东,洪炳荣,朱莹.基.于HSI颜色空间的多机器人识别研究[J].哈尔滨工业大学学报,2004,36(7)：928-930.
[191]阴炳皓,赵臣,韩晓军.基于改进的HSI空间模型的目标搜索方法[J].河北工业大学学报,2003,32(1)：6-10.