基于微透镜阵列的三维物体识别
|
摘要
光学系统对二维图像进行识别具有非接触、速度快、并行处理和平移不变性等优点，从而得到了广泛应用。但光学系统只能对二维信息进行处理，不能直接实现三维物体的识别，而必须首先将三维物体的信息转换成二维信息。
本文提出一种基于微透镜阵列多视角成像特点，将三维物体的深度信息转化为二维的透射像阵列的角度信息，利用光学二维图像识别技术，实现对三维物体识别的方法。并对识别过程进行了理论分析和计算，用匹配滤波的方法实现了对三维物体骰子的实时识别。实验结果表明，本方法的相关识别能力较高，并且具有很强的灵活性，对于有微小旋转、微小平移的三维物体也可进行识别。
在该方法的基础上，接着讨论了其对于具有小角度旋转的三维物体的旋转不变识别，并进行了实验验证，得到了比较好的识别效果。并且实现了实时识别，使该方法的应用范围进一步扩大。随后对得到的透射像阵列图像，应用综合判别函数，用计算机进行模拟实验，对三维物体骰子的相同面、不同面旋转实现了旋转不变识别，得到了比较好的识别效果，从而得到一种新的对三维物体进行旋转不变识别的方法。
Because of non-contact, speed, parallel processing and shift invariant, two-dimensional(2-D) object recognition by use of optical system is be used abroad. But optical system only can be used for processing of 2-D information, not be used for 3-D object recognition, so 3-D object information must be transformed for 2-D information firstly.
A novel method for three-dimensional(3-D) object recognition by use of microlens array is proposed. The conversion of depth information of 3-D objects to 2-D elemental images by use of the characteristic of microlens array makes it is possible to recognition by optical processing. Correlative analysis and calculations has been done for the process of recognition, and real-time recognition of dice ,a 3-D object ,has been accomplished by use of the method of match filtering. The result showed that the proposed method performed better, and it can be used for recognition of slightly rotated and slightly shifted object flexibly.
3-D object micro-angle rotation invariant recognition is discussed continually, The experiment result of 3-D object real-time recognition showed that the proposed method performed better, and then, A novel method for 3-D object rotation invariant recognition by use of synthetic discriminant function(SDF) is received. The computer simulate experiment for rotation invariant recognition for dice, a 3-D object has been accomplished.
本文提出一种基于微透镜阵列多视角成像特点，将三维物体的深度信息转化为二维的透射像阵列的角度信息，利用光学二维图像识别技术，实现对三维物体识别的方法。并对识别过程进行了理论分析和计算，用匹配滤波的方法实现了对三维物体骰子的实时识别。实验结果表明，本方法的相关识别能力较高，并且具有很强的灵活性，对于有微小旋转、微小平移的三维物体也可进行识别。
在该方法的基础上，接着讨论了其对于具有小角度旋转的三维物体的旋转不变识别，并进行了实验验证，得到了比较好的识别效果。并且实现了实时识别，使该方法的应用范围进一步扩大。随后对得到的透射像阵列图像，应用综合判别函数，用计算机进行模拟实验，对三维物体骰子的相同面、不同面旋转实现了旋转不变识别，得到了比较好的识别效果，从而得到一种新的对三维物体进行旋转不变识别的方法。
Because of non-contact, speed, parallel processing and shift invariant, two-dimensional(2-D) object recognition by use of optical system is be used abroad. But optical system only can be used for processing of 2-D information, not be used for 3-D object recognition, so 3-D object information must be transformed for 2-D information firstly.
A novel method for three-dimensional(3-D) object recognition by use of microlens array is proposed. The conversion of depth information of 3-D objects to 2-D elemental images by use of the characteristic of microlens array makes it is possible to recognition by optical processing. Correlative analysis and calculations has been done for the process of recognition, and real-time recognition of dice ,a 3-D object ,has been accomplished by use of the method of match filtering. The result showed that the proposed method performed better, and it can be used for recognition of slightly rotated and slightly shifted object flexibly.
3-D object micro-angle rotation invariant recognition is discussed continually, The experiment result of 3-D object real-time recognition showed that the proposed method performed better, and then, A novel method for 3-D object rotation invariant recognition by use of synthetic discriminant function(SDF) is received. The computer simulate experiment for rotation invariant recognition for dice, a 3-D object has been accomplished.
引文
[1]宋菲君,S．Jutamulia．近代光学信息处理[M]．北京：北京大学出版社，1998．
[2]A.Vander Lugt, Signal detection by complex spatial filtering, IEEE Trans Inf. Theory, 1964(IT-10),139-145.
[3]C.S.Weaer and J.W.Goodman, A technique for optically convolving two functions, Appl.Opt.. 1966(5),1248～1249.
[4]J.E.Rau, Detection of difference in real distributions, J.Opt.Soc.Am,1966(56),1490-1494.
[5]J.L.Horner, Light utilization in optical correlators, Appl.Opt.,1982,21(24),4511-4514.
[6]J.L.Horner and J.R.Leger, Pattern recognition with binary phase-only filters, Appl.Opt., 1985,24(5),609-611.
[7]B.Javidi, Nonlinear matched filter based optical correlation, Appl. Opt, 1989,28(21),4518-4520
[8]B.Javidi, Norilinear joint power spectrum based optical correlation, Appl. Opt., 1989, 25(12), 2358-2367
[9]S.Zhong, J.Jiang, S.Liu,C.Li, Binary joint transform correlation based on differenttial processing of the joint transform power spectrum, Appl.Opt.,1997, 36(8), 1776-1780.
[10]V.Namias, the Fractional order Fourier transform and its application to quantum mechanics, J.Inst.Maths Applics, 1980(25),241-265.
[11]刘思敏，郭儒，许京军．光折变非线性光学及其应用[M]．北京：科学出版社,2004．
[12]J.Khoury and M.Cronin-Golomb, Photorefractive two-beam-coupling nonlinear joint- transform correlator, J.Opt.Soc.Am.B., 1994,11(11),2167-2174.
[13]S.Shin and B.Javidi, Three-dimensional object recognition by use of a photorefractive volume holographic processor, Opt.Lett., 2001,26(15),1161～1163
[14]赵建林，许其推，杨德兴，谢良平，杨东升．基于KNSBN：Cu晶体的光折变联合变换相关器， 光子学报，2002，31(5)，557—560．
[15]H.Zhang, C.M.Cartwright, et al. Experimental implementation of a photorefractive joint transform correlator with circular harmonic filters, Opt.commun., 2000(173),129～136
[16]J.Khoruy, P.D.Gianino, C.L.Woods, Engineering aspects of the two-beam-coupling correlator, Opt.Eng., 2000,39(5),1177-1183.
[17]A.D.Gara, Real-time tracking of moving objects by optical correlation, Appl.Opt., 1979(18),172～174.
[18]F.T.S.Yu and X.J.Lu, A programmable joint transform correlator, Opt.Commun., 1984(52), 10-16.
[19]J.G.Duthie and J.Upatnieks, Compact real-time coherent optical correlator, Opt.Eng., 1984(23),7-11.
[20]Y.N.Hsu and H.H.Arsenault, Optical pattern recognition using circular harmonic expansion, Appl. Opt., 1982(21),4016-4019.
[21]F.T.S.Yu, X.Y.Li, E.Tam, S.Jutamulia, D.A.Gregory, Rotation-invariant pattern recognition with a programmable joint transform correlator, Appl.Opt.,1989(28),4725～4727.
[22]D.Casasent and D.Psaltis, Scale invariant optical transform, Opt.Eng.,1976(15),258-261.
[23]O.Bryngdahl, Geometrical transformations in optics, Jour.Opt.Soc.Am.,1974(64),1092～1099.
[24]钟黔川，刘艺，王仕璠．基于逆滤波器的旋转不变匹配滤波相关识别．中国激光，2002， 29(10)，941-944．
[25]刘秋武，刘艺，王仕瑶．基于尺度可变的傅氏变换实现比例不变的相关识别．激光杂志，2004,25(3)，61-63．
[26]赵昱，申弦国．四元量化的综合鉴别函数滤波器实现比例不变相关识别．光子学报，2005， 34(8)，1156-1159
[27]B.Javidi and E.Tajahuerce. Three-dimensional object recognition by use of digital holography. Opt.Lett.2000, 25,610-612.
[28]Thomas J.Naughton, Yann Frauel, Bahram Javidi, Enrique Tajahuerce. Compression of digital holograms for three-dimensional object reconstruction and recognition. Appl.Opt., 2002, 41(20),4124～4132
[29]B.Javidi, E.Tajahuerc,T.J.Naughton, et al. Three-dimensional image encryption, transmission and processing by using digital holography. Proc.of SPIE. 2005, Vol. 5954,595403.
[30]O.Matoba, T.J.Naughton, Y.Frauel, N.Bertaux, B.Javidi. Real-time three dimensional object recognition by use of a phase-encoded digital hologram. Appl.Opt.,2002,41(29),6187-6192.
[31]A.Nelleri, U.Gopinathan, J.Joseph, K.Singh. Three-dimensional object recognition from digital Fresnel hologram by wavelet matched filtering. Opt.Commun.,2006(259),499～506.
[32]姜美花，苏显渝，刘元坤．基于结构照明的三位物体识别新方．光电子·激光， 2003，14(8)，869-872．
[33]王海霞，苏显渝，吕静．基于莫尔条纹的三维物体相关识．光电子·激光， 2005，16(3)，349～353．
[34]李庆，周曼丽，柳健．基于多分辨率格网的三位物体识别方．电子学报,2001,29(7)，891-894．
[35]宋万忠，苏显渝．基于结构光投影的三维物体识别．光电子·激光，1999，10(1)，59-62．
[36]林应强，吴立德．基于模型的三维物体识别．自动化学报，1997,23(6)，756～761．
[37]曾接贤，陈震，储君，黎明．基于形态图表示的三维物体识别算法．计算机应用,2003,23(2)，9～12．
[38]B.Javidi, E.Tajahuerc, Manuel Martinez-Corral,et al. New developments in active and passive 3D image sensing, visualization, and processing. Proc. of SPIE. 2005, Vol. 5986,598601
[39]A.E.Shortt, T.J.Naughton, B.Javidi. Compressing of.digital holograms of three-dimensional objects using wavelets. Opt.Express.2006,14(7),2625～2630.
[40]O..Matoba, E.Tajahuerce, B.Javidi. Real-time three-dimension object recognition with multiple perspectives imaging. Appl.Opt., 2001,40(20),3318～3325.
[41]S.H.Hong, J.S.Jang, B.Javidi. Three-dimensional volumetric object reconstruction using computational integral imaging. Opt.Express.2004,12(3),483～491.
[42]F.Okano, J.Arai, H.Hoshino, I.Yiyama. Three-dimensional video system based on integral photograph. Opt.Eng.,1999,38,1072～1077.
[43]Y.Frauel, E.Tajahuerce, O.Matoba, A.Castro, B.Javidi. Comparison of passive ranging integral imaging an active imaging digital holography for three-dimensional object recognition. Appl. Opt.,2004 , 43 , 452～462.
[44]王仕璠．信息光学理论与应用[M]．北京：北京邮电大学出版社，2004．
[45]D.Casasent, D.Psaltis, Scale invariant optical correlation using Mellin transform. Opt. Commun.,1976,17,59.
[46]Y.Saito, S.Komatsu,H.Ohzu, Scale and rotation invariant real time optical correlation using computer generated hologram. Opt. Commun., 1983,47,8-11.
[47]B.Loiseaux, G:Illiaquer, J.P.Huignard, Dynamic optical cross-correlator using a liquid crystal light valve and a BSO crystal in the Fourier plane. Opt.Eng.,1985,24,144-149.
[48]F.T.S.Yu, X.J.Lu, A programmable joint transform correlator, Opt.Commun.,1984,52,10-16.
[49]S.Jutamulia and T.Asakura, Rotation-invariant joint transform correlator, Appl.Opt.,1994,33, 5440-5442.
[50]S.Jutamulia and D.A.Gregory, Photo-compact-disk-based optical correlator, Appl.Opt., 1993, 32,5092-5094.
[51]段作梁，刘艺，王仕璠．用全光联合变换实现目标识别．激光杂志，2000，21(4)，9-10．
[52]秦玉文，黄战华，张以谟．实时光电混合联合变换相关器单元的实验研究．光学学报，1994， 14(8)，829～833．
[53]D.Casasent, Unified synthetic discriminant function computational formulation, Appl.Opt., 1984, 23(10), 1620-1627.
[54]何万涛，连铜淑．综合判别函数相关器实验研究．激光技术．1996，20(2)，122-125．
[55]孙红辉，李晓建，张震仁．基于计算机处理的畸变图像相关识别．机电工程技术，2004， 23(6)，44-45．
[56]仁智斌．折射型微透镜及微透镜阵列光学性质与制作技术的研究。中国科学院研究生院博士学位论文，2004．
[2]A.Vander Lugt, Signal detection by complex spatial filtering, IEEE Trans Inf. Theory, 1964(IT-10),139-145.
[3]C.S.Weaer and J.W.Goodman, A technique for optically convolving two functions, Appl.Opt.. 1966(5),1248～1249.
[4]J.E.Rau, Detection of difference in real distributions, J.Opt.Soc.Am,1966(56),1490-1494.
[5]J.L.Horner, Light utilization in optical correlators, Appl.Opt.,1982,21(24),4511-4514.
[6]J.L.Horner and J.R.Leger, Pattern recognition with binary phase-only filters, Appl.Opt., 1985,24(5),609-611.
[7]B.Javidi, Nonlinear matched filter based optical correlation, Appl. Opt, 1989,28(21),4518-4520
[8]B.Javidi, Norilinear joint power spectrum based optical correlation, Appl. Opt., 1989, 25(12), 2358-2367
[9]S.Zhong, J.Jiang, S.Liu,C.Li, Binary joint transform correlation based on differenttial processing of the joint transform power spectrum, Appl.Opt.,1997, 36(8), 1776-1780.
[10]V.Namias, the Fractional order Fourier transform and its application to quantum mechanics, J.Inst.Maths Applics, 1980(25),241-265.
[11]刘思敏，郭儒，许京军．光折变非线性光学及其应用[M]．北京：科学出版社,2004．
[12]J.Khoury and M.Cronin-Golomb, Photorefractive two-beam-coupling nonlinear joint- transform correlator, J.Opt.Soc.Am.B., 1994,11(11),2167-2174.
[13]S.Shin and B.Javidi, Three-dimensional object recognition by use of a photorefractive volume holographic processor, Opt.Lett., 2001,26(15),1161～1163
[14]赵建林，许其推，杨德兴，谢良平，杨东升．基于KNSBN：Cu晶体的光折变联合变换相关器， 光子学报，2002，31(5)，557—560．
[15]H.Zhang, C.M.Cartwright, et al. Experimental implementation of a photorefractive joint transform correlator with circular harmonic filters, Opt.commun., 2000(173),129～136
[16]J.Khoruy, P.D.Gianino, C.L.Woods, Engineering aspects of the two-beam-coupling correlator, Opt.Eng., 2000,39(5),1177-1183.
[17]A.D.Gara, Real-time tracking of moving objects by optical correlation, Appl.Opt., 1979(18),172～174.
[18]F.T.S.Yu and X.J.Lu, A programmable joint transform correlator, Opt.Commun., 1984(52), 10-16.
[19]J.G.Duthie and J.Upatnieks, Compact real-time coherent optical correlator, Opt.Eng., 1984(23),7-11.
[20]Y.N.Hsu and H.H.Arsenault, Optical pattern recognition using circular harmonic expansion, Appl. Opt., 1982(21),4016-4019.
[21]F.T.S.Yu, X.Y.Li, E.Tam, S.Jutamulia, D.A.Gregory, Rotation-invariant pattern recognition with a programmable joint transform correlator, Appl.Opt.,1989(28),4725～4727.
[22]D.Casasent and D.Psaltis, Scale invariant optical transform, Opt.Eng.,1976(15),258-261.
[23]O.Bryngdahl, Geometrical transformations in optics, Jour.Opt.Soc.Am.,1974(64),1092～1099.
[24]钟黔川，刘艺，王仕璠．基于逆滤波器的旋转不变匹配滤波相关识别．中国激光，2002， 29(10)，941-944．
[25]刘秋武，刘艺，王仕瑶．基于尺度可变的傅氏变换实现比例不变的相关识别．激光杂志，2004,25(3)，61-63．
[26]赵昱，申弦国．四元量化的综合鉴别函数滤波器实现比例不变相关识别．光子学报，2005， 34(8)，1156-1159
[27]B.Javidi and E.Tajahuerce. Three-dimensional object recognition by use of digital holography. Opt.Lett.2000, 25,610-612.
[28]Thomas J.Naughton, Yann Frauel, Bahram Javidi, Enrique Tajahuerce. Compression of digital holograms for three-dimensional object reconstruction and recognition. Appl.Opt., 2002, 41(20),4124～4132
[29]B.Javidi, E.Tajahuerc,T.J.Naughton, et al. Three-dimensional image encryption, transmission and processing by using digital holography. Proc.of SPIE. 2005, Vol. 5954,595403.
[30]O.Matoba, T.J.Naughton, Y.Frauel, N.Bertaux, B.Javidi. Real-time three dimensional object recognition by use of a phase-encoded digital hologram. Appl.Opt.,2002,41(29),6187-6192.
[31]A.Nelleri, U.Gopinathan, J.Joseph, K.Singh. Three-dimensional object recognition from digital Fresnel hologram by wavelet matched filtering. Opt.Commun.,2006(259),499～506.
[32]姜美花，苏显渝，刘元坤．基于结构照明的三位物体识别新方．光电子·激光， 2003，14(8)，869-872．
[33]王海霞，苏显渝，吕静．基于莫尔条纹的三维物体相关识．光电子·激光， 2005，16(3)，349～353．
[34]李庆，周曼丽，柳健．基于多分辨率格网的三位物体识别方．电子学报,2001,29(7)，891-894．
[35]宋万忠，苏显渝．基于结构光投影的三维物体识别．光电子·激光，1999，10(1)，59-62．
[36]林应强，吴立德．基于模型的三维物体识别．自动化学报，1997,23(6)，756～761．
[37]曾接贤，陈震，储君，黎明．基于形态图表示的三维物体识别算法．计算机应用,2003,23(2)，9～12．
[38]B.Javidi, E.Tajahuerc, Manuel Martinez-Corral,et al. New developments in active and passive 3D image sensing, visualization, and processing. Proc. of SPIE. 2005, Vol. 5986,598601
[39]A.E.Shortt, T.J.Naughton, B.Javidi. Compressing of.digital holograms of three-dimensional objects using wavelets. Opt.Express.2006,14(7),2625～2630.
[40]O..Matoba, E.Tajahuerce, B.Javidi. Real-time three-dimension object recognition with multiple perspectives imaging. Appl.Opt., 2001,40(20),3318～3325.
[41]S.H.Hong, J.S.Jang, B.Javidi. Three-dimensional volumetric object reconstruction using computational integral imaging. Opt.Express.2004,12(3),483～491.
[42]F.Okano, J.Arai, H.Hoshino, I.Yiyama. Three-dimensional video system based on integral photograph. Opt.Eng.,1999,38,1072～1077.
[43]Y.Frauel, E.Tajahuerce, O.Matoba, A.Castro, B.Javidi. Comparison of passive ranging integral imaging an active imaging digital holography for three-dimensional object recognition. Appl. Opt.,2004 , 43 , 452～462.
[44]王仕璠．信息光学理论与应用[M]．北京：北京邮电大学出版社，2004．
[45]D.Casasent, D.Psaltis, Scale invariant optical correlation using Mellin transform. Opt. Commun.,1976,17,59.
[46]Y.Saito, S.Komatsu,H.Ohzu, Scale and rotation invariant real time optical correlation using computer generated hologram. Opt. Commun., 1983,47,8-11.
[47]B.Loiseaux, G:Illiaquer, J.P.Huignard, Dynamic optical cross-correlator using a liquid crystal light valve and a BSO crystal in the Fourier plane. Opt.Eng.,1985,24,144-149.
[48]F.T.S.Yu, X.J.Lu, A programmable joint transform correlator, Opt.Commun.,1984,52,10-16.
[49]S.Jutamulia and T.Asakura, Rotation-invariant joint transform correlator, Appl.Opt.,1994,33, 5440-5442.
[50]S.Jutamulia and D.A.Gregory, Photo-compact-disk-based optical correlator, Appl.Opt., 1993, 32,5092-5094.
[51]段作梁，刘艺，王仕璠．用全光联合变换实现目标识别．激光杂志，2000，21(4)，9-10．
[52]秦玉文，黄战华，张以谟．实时光电混合联合变换相关器单元的实验研究．光学学报，1994， 14(8)，829～833．
[53]D.Casasent, Unified synthetic discriminant function computational formulation, Appl.Opt., 1984, 23(10), 1620-1627.
[54]何万涛，连铜淑．综合判别函数相关器实验研究．激光技术．1996，20(2)，122-125．
[55]孙红辉，李晓建，张震仁．基于计算机处理的畸变图像相关识别．机电工程技术，2004， 23(6)，44-45．
[56]仁智斌．折射型微透镜及微透镜阵列光学性质与制作技术的研究。中国科学院研究生院博士学位论文，2004．