工业流水线上连续帧图像配准及高光去除
|
摘要
物体上的高光直接影响工业检测、模式识别和计算机视觉等领域中后续处理的算法性能。如何检测和消除图像中的高光区域一直是个热点问题。
现在已有的去高光处理方法主要是针对单幅图像的,但是单幅图像的处理比较困难,去除高光的结果很难到达预期。本文介绍了一种基于连续帧图像配准及高光去除的方法,主要利用了连续帧图像之间的互补信息。该解决方案包括两个主要部分:图像配准和图像融合。
首先,利用特征检测及其特征描述或者其他图像配准方法,对连续帧图像进行自动配准。
其次,在连续帧图像被配准后,对配准后的图像进行融合。
最后,输出去除高光后的图像。
图像配准模块主要介绍了一种基于SURF的连续帧图像配准方法,虽然该方法能比较好处理大部分图像,但由于SURF对纹理特征比较少的图像特征提取效果并不好。为此,我们提出了一种基于Canny的主轮廓线配准方法。利用这两种图像配准方法,我们可以比较好的完成图像配准模块的工作,然后进行图像融合。经过多次实验,我们认为该方法用于消除或消弱高光区域有比较好的效果,有一定的理论和应用价值。
Luster immediate influences the following algorithm performance in the field of Industry Detection、Pattern Recognition and Computer Vision. It is always the hot topic that how to detect and eliminate the luster region in the image.
As we know, the existing Luster removal technology is mainly based on single image. But it is very difficult for us to process single image to eliminate the luster region, and the result of processing single image to eliminate the luster region is not so good. This article introduces a solution that Luster removal image composition technology based on continual frame image registration, and this solution is mainly concerning the supplementary information between the continual frame images. This solution is mainly including two parts: Image registration and Image fusion.
First, we register the animation images by the way of feature detection and feature description or other image registration methods.
Second, we fuse the registered images after matching
Last, we output the luster–removed image.
This article mainly introduces a image registration method based on SURF in the Image registration module. This method is good at processing the most of images, but this method is not good at the image which contains few textural property. So, we propose a method which we called All Principal Edge Matching based on Canny. We can complete continual frame image registration by using these two image registration methods, and the final step is fusing the registered continual frame images. The experiment indicates that this method is good for eliminating the luster, and this solution has certain value in the field of theory and application.
现在已有的去高光处理方法主要是针对单幅图像的,但是单幅图像的处理比较困难,去除高光的结果很难到达预期。本文介绍了一种基于连续帧图像配准及高光去除的方法,主要利用了连续帧图像之间的互补信息。该解决方案包括两个主要部分:图像配准和图像融合。
首先,利用特征检测及其特征描述或者其他图像配准方法,对连续帧图像进行自动配准。
其次,在连续帧图像被配准后,对配准后的图像进行融合。
最后,输出去除高光后的图像。
图像配准模块主要介绍了一种基于SURF的连续帧图像配准方法,虽然该方法能比较好处理大部分图像,但由于SURF对纹理特征比较少的图像特征提取效果并不好。为此,我们提出了一种基于Canny的主轮廓线配准方法。利用这两种图像配准方法,我们可以比较好的完成图像配准模块的工作,然后进行图像融合。经过多次实验,我们认为该方法用于消除或消弱高光区域有比较好的效果,有一定的理论和应用价值。
Luster immediate influences the following algorithm performance in the field of Industry Detection、Pattern Recognition and Computer Vision. It is always the hot topic that how to detect and eliminate the luster region in the image.
As we know, the existing Luster removal technology is mainly based on single image. But it is very difficult for us to process single image to eliminate the luster region, and the result of processing single image to eliminate the luster region is not so good. This article introduces a solution that Luster removal image composition technology based on continual frame image registration, and this solution is mainly concerning the supplementary information between the continual frame images. This solution is mainly including two parts: Image registration and Image fusion.
First, we register the animation images by the way of feature detection and feature description or other image registration methods.
Second, we fuse the registered images after matching
Last, we output the luster–removed image.
This article mainly introduces a image registration method based on SURF in the Image registration module. This method is good at processing the most of images, but this method is not good at the image which contains few textural property. So, we propose a method which we called All Principal Edge Matching based on Canny. We can complete continual frame image registration by using these two image registration methods, and the final step is fusing the registered continual frame images. The experiment indicates that this method is good for eliminating the luster, and this solution has certain value in the field of theory and application.
引文
[1] Wolff LB. Using polarization to separate reflection components. In: Proc. of the IEEE Computer Vision and Pattern Recognition. 1989. 363-369.
[2] Sato Y, Ikeuchi K. Temporal-Color space analysis of reflection. Journal of the Optical Society of America A, 1994,11(11).
[3] Nayar SK, Fang X, Boult TE. Removal of specularities using color and polarization. In: Proc. of the IEEE Computer Vision and Pattern Recognition. 1993. 583~590.
[4] Klinker GJ, Shafer SA, Kanade T. The measurement of highlights in color images. International Journal of Computer Vision, 1990,2:7-32.
[5] Shafer SA. Using color to separate reflection components. COLOR Research and Application, 1985,10(4):210-218.
[6] Noak CL, Shafer SA. Anatomy of a color histogram. In: Proc. of the IEEE Computer Vision and Pattern Recognition. 1992. 599-605.
[7] Lee H-C. Method for computing the scene-illuminant chromaticity from specular highlights. Journal of the Optical Society of America A, 1986,1(10).
[8] Brainard DH, Freeman WT. Bayesian color constancy. Journal of the Optical Society of America A, 1997,14(7).
[9] GUILLERMO S. Image inpainting [C] Proceeding of SINGRAPH’2000. ACM Press, 2000:411-424
[10]谭平,杨杰.用于去除单张图像高光的光照约束补色[J].软件学报,2004,15(1):33-40.
[11] L.G Brown,A survey of Image Registration Techniques.ACM Computing Surveys. 1992:pp.326.376
[12]张祖勋,张剑清,数字摄影测量学,武汉:武汉测绘科技大学出版社.1996
[13] B. Srinivasa, Reddy, and B. N. Chaterji, An FFT Based Technique for Translation, Rotation, and Scale-Invariant Image Registration, IEEE rans. on Image Porcessing, 1996,
[14]沈邦乐,计算机图像处理,北京:解放军出版社,1995 5( 8):1266-1271 [l5] M.K.Hu,Visual pattern recognition by moment invariants, IRE Trans. On Information Th eory,1962,IT8 :17 9-187
[16] Chris Harris and M . Stephen, A Combined Coner and Edge Detector . Alvey Vision Conference.1988.PP.147-152
[17] S.M.Smith and J.M.Brady, SUSAN-a new approach to low level image processing, International Jounral of Computer Vision,1995,23 (1):45-78
[18] M .G. Fonseca, and H. M. Costa, Automatic Registration of Satellite Images, Brazilian Symposium on Graphic Computation and Image Processing, 10, C ampos de Jordao, 1997. Proceedings. Los Alamitos:IEEE Computer Society,1997:219-22
[19] Herbert Bay, Tinne Tuytelaars, and Luc Van Gool, SURF:Speeded Up Robust Features, ECCV, 2006
[21] B. S. Reddy and B. N. Chatterji, An FFT-based technique for translation, rotation, and scale-invariant image registration. IEEE Transactions on Image Processing. 1995, 5(8):1266-1271
[22] R. Szeliski, Video mosaics for virtual environments. Computer Graphics and Applications, IEEE. 1996, 16(2):22-30
[23] M. Muler, W. Kruger and G.. Gaur, Robust image registration for fuison. Information Fusion. 2007,8(4):347-353
[24] D. Xiaolong and S. Khorram, A feature-based image registration algorithm using improved chain-code representation combined with invariant moments. IEEE Transaction on Geoscience and Remote Sensing. 1999, 37(5): 2351-2362
[25] L. Hui, B. S. Manjunath and S. K. Mitra, A contour-based approach to multisensor image registration. IEEE Transactions on Image Processing. 1995, 4(3):320-334
[26] F. Isgr and M. Pilu, A fase and robust image registration method on an early consensus paradigm. Pattern Recognition Letters. 2004, 25(8): 943-954
[27] X. Peng, W. Chen and Q. Ma, Hausdorff Distance Based Non-rigid Image Registration Using Feature Points. Communications, Circuits and Systems Proceedings, 2006 International Conference on. 2006, 1:442-445
[28] D. G. Lowe, Distinctive Image Feature from Scale-Invariant Keypoints. Int. J. Comput. Vision. 2004,60(2):91-110
[29] L. G.. Brown, A survey of Image Registration Techniques. ACM Computing Surveys. 1992:pp.326-376
[30] S. H. F. Barnea D. I, A class of algorithms for digital image registration. IEEE Transactions on Computers. 1976, C-21(2): pp.179-186
[31] P. Viola and W. M. Wells, III, Alignment by maximization of mutual information. Proceedings of Fifth International Conference on Computer Vision. 1995,16-23
[32] S. Alliney and C. Morandi, Digital Image Registration Using Projections. IEEE Transaction on Pattern Analysis and Machine Intelligence. 1986, PAMI-8(2):222-233
[33] G. Wolberg and S. Zokai, Robust image registration using log-polar transform. Proceedings of International Conference on Image Processing. 2000, 1: 493-496 vol.1
[34] R. E. W. Refael C. Gonzalez, Digital Image Processing. UTK: Prentice Hall, 2006, pp. 460-514
[35] H. T. Sheu and W. C. Hu, A rotationally invariant two-phase scheme for corner detection. Pattern Recognition. 1996, 29(5): 819-828
[36] W. Qian, Z. Fu, L. Liu and Z. Deng, Image registration based on feature extraction and voting strategy. Communications, Circuits and Systems, 2008. ICCCAS 2008. International Conference on. 2008, 706-709
[37] J. Canny A Computational Approach to Edge Detection[J], IEEE Transactions on Pattern Analysis and Machine Intelligence vol 8. No.6, Nov 1986
[38] Lee J. Haralick R, Shapiro L.Morphologic edge detection. IEEE Transactions on Robotics and Automation, 1987, 3(2): 142-156
[39] Lallier, E.; Farooq, M., "A real time pixel-level based image fusion via adaptive weight averaging", Proceedings of the Third International Conference on Information Fusion vol.2, pp.WEC3/3-13, 2000
[40] Mitianoudis, N; Stathaki, T, "Pixel-based and region-based image fusion schemes using ICA bases", INFORMATION FUSION, vol.8, NO.2, pp.131-142, 2007
[41] L.J. Chipman, T.M. Orr and L.N. Lewis, Wavelets and image fusion, IEEE Transactions on Image Processing, 3, pp. 248-251, 1995.
[42] E. Adelson, C.H. Anderson, J.R. Bergen, P.J. Burt and J.M. Ogden,‘Pyramid methods in image processing’, RCA
[43] P.J. Burt and E.H. Adelson,‘The Laplacian pyramid as a compact image code’, IEEE Trans. Commun. COM-31, pp.532-540, 1983
[44] A. Toet and J. Walraven,‘New false color mapping for image fusion’, Optical Engineering, 1996
[45] Hall D.L,Llinas.J, An introduction to multi-sensor data fusion[J].Proc. of IEEE,1997,85(1):pp.6-23.
[46] Van GenderenJ.L.,Pohl C.,Image fusion:Issues,techniques and applications,Intelligent Image Fusion, Proceedings EARSEL Workshop,Strasbourg, France, 1994,edited by Van Genderen.J.L and Cappellini.V, pp:18-26.
[47] Ehlers M., Multisensor image fusion techniques in remote sensing. Photogrammetric Engeneering and Remote Sensing.Vol.46, pp. 19-30,1991
[48]苗启广,王宝树,基于非负矩阵分解的多聚焦图像融合研究[J],光学学报,2005,25(6):755-759
[49] Waltz E.,and Llinas J. Multisensor Data Fusion.Boston:Artech House, 1990
[2] Sato Y, Ikeuchi K. Temporal-Color space analysis of reflection. Journal of the Optical Society of America A, 1994,11(11).
[3] Nayar SK, Fang X, Boult TE. Removal of specularities using color and polarization. In: Proc. of the IEEE Computer Vision and Pattern Recognition. 1993. 583~590.
[4] Klinker GJ, Shafer SA, Kanade T. The measurement of highlights in color images. International Journal of Computer Vision, 1990,2:7-32.
[5] Shafer SA. Using color to separate reflection components. COLOR Research and Application, 1985,10(4):210-218.
[6] Noak CL, Shafer SA. Anatomy of a color histogram. In: Proc. of the IEEE Computer Vision and Pattern Recognition. 1992. 599-605.
[7] Lee H-C. Method for computing the scene-illuminant chromaticity from specular highlights. Journal of the Optical Society of America A, 1986,1(10).
[8] Brainard DH, Freeman WT. Bayesian color constancy. Journal of the Optical Society of America A, 1997,14(7).
[9] GUILLERMO S. Image inpainting [C] Proceeding of SINGRAPH’2000. ACM Press, 2000:411-424
[10]谭平,杨杰.用于去除单张图像高光的光照约束补色[J].软件学报,2004,15(1):33-40.
[11] L.G Brown,A survey of Image Registration Techniques.ACM Computing Surveys. 1992:pp.326.376
[12]张祖勋,张剑清,数字摄影测量学,武汉:武汉测绘科技大学出版社.1996
[13] B. Srinivasa, Reddy, and B. N. Chaterji, An FFT Based Technique for Translation, Rotation, and Scale-Invariant Image Registration, IEEE rans. on Image Porcessing, 1996,
[14]沈邦乐,计算机图像处理,北京:解放军出版社,1995 5( 8):1266-1271 [l5] M.K.Hu,Visual pattern recognition by moment invariants, IRE Trans. On Information Th eory,1962,IT8 :17 9-187
[16] Chris Harris and M . Stephen, A Combined Coner and Edge Detector . Alvey Vision Conference.1988.PP.147-152
[17] S.M.Smith and J.M.Brady, SUSAN-a new approach to low level image processing, International Jounral of Computer Vision,1995,23 (1):45-78
[18] M .G. Fonseca, and H. M. Costa, Automatic Registration of Satellite Images, Brazilian Symposium on Graphic Computation and Image Processing, 10, C ampos de Jordao, 1997. Proceedings. Los Alamitos:IEEE Computer Society,1997:219-22
[19] Herbert Bay, Tinne Tuytelaars, and Luc Van Gool, SURF:Speeded Up Robust Features, ECCV, 2006
[21] B. S. Reddy and B. N. Chatterji, An FFT-based technique for translation, rotation, and scale-invariant image registration. IEEE Transactions on Image Processing. 1995, 5(8):1266-1271
[22] R. Szeliski, Video mosaics for virtual environments. Computer Graphics and Applications, IEEE. 1996, 16(2):22-30
[23] M. Muler, W. Kruger and G.. Gaur, Robust image registration for fuison. Information Fusion. 2007,8(4):347-353
[24] D. Xiaolong and S. Khorram, A feature-based image registration algorithm using improved chain-code representation combined with invariant moments. IEEE Transaction on Geoscience and Remote Sensing. 1999, 37(5): 2351-2362
[25] L. Hui, B. S. Manjunath and S. K. Mitra, A contour-based approach to multisensor image registration. IEEE Transactions on Image Processing. 1995, 4(3):320-334
[26] F. Isgr and M. Pilu, A fase and robust image registration method on an early consensus paradigm. Pattern Recognition Letters. 2004, 25(8): 943-954
[27] X. Peng, W. Chen and Q. Ma, Hausdorff Distance Based Non-rigid Image Registration Using Feature Points. Communications, Circuits and Systems Proceedings, 2006 International Conference on. 2006, 1:442-445
[28] D. G. Lowe, Distinctive Image Feature from Scale-Invariant Keypoints. Int. J. Comput. Vision. 2004,60(2):91-110
[29] L. G.. Brown, A survey of Image Registration Techniques. ACM Computing Surveys. 1992:pp.326-376
[30] S. H. F. Barnea D. I, A class of algorithms for digital image registration. IEEE Transactions on Computers. 1976, C-21(2): pp.179-186
[31] P. Viola and W. M. Wells, III, Alignment by maximization of mutual information. Proceedings of Fifth International Conference on Computer Vision. 1995,16-23
[32] S. Alliney and C. Morandi, Digital Image Registration Using Projections. IEEE Transaction on Pattern Analysis and Machine Intelligence. 1986, PAMI-8(2):222-233
[33] G. Wolberg and S. Zokai, Robust image registration using log-polar transform. Proceedings of International Conference on Image Processing. 2000, 1: 493-496 vol.1
[34] R. E. W. Refael C. Gonzalez, Digital Image Processing. UTK: Prentice Hall, 2006, pp. 460-514
[35] H. T. Sheu and W. C. Hu, A rotationally invariant two-phase scheme for corner detection. Pattern Recognition. 1996, 29(5): 819-828
[36] W. Qian, Z. Fu, L. Liu and Z. Deng, Image registration based on feature extraction and voting strategy. Communications, Circuits and Systems, 2008. ICCCAS 2008. International Conference on. 2008, 706-709
[37] J. Canny A Computational Approach to Edge Detection[J], IEEE Transactions on Pattern Analysis and Machine Intelligence vol 8. No.6, Nov 1986
[38] Lee J. Haralick R, Shapiro L.Morphologic edge detection. IEEE Transactions on Robotics and Automation, 1987, 3(2): 142-156
[39] Lallier, E.; Farooq, M., "A real time pixel-level based image fusion via adaptive weight averaging", Proceedings of the Third International Conference on Information Fusion vol.2, pp.WEC3/3-13, 2000
[40] Mitianoudis, N; Stathaki, T, "Pixel-based and region-based image fusion schemes using ICA bases", INFORMATION FUSION, vol.8, NO.2, pp.131-142, 2007
[41] L.J. Chipman, T.M. Orr and L.N. Lewis, Wavelets and image fusion, IEEE Transactions on Image Processing, 3, pp. 248-251, 1995.
[42] E. Adelson, C.H. Anderson, J.R. Bergen, P.J. Burt and J.M. Ogden,‘Pyramid methods in image processing’, RCA
[43] P.J. Burt and E.H. Adelson,‘The Laplacian pyramid as a compact image code’, IEEE Trans. Commun. COM-31, pp.532-540, 1983
[44] A. Toet and J. Walraven,‘New false color mapping for image fusion’, Optical Engineering, 1996
[45] Hall D.L,Llinas.J, An introduction to multi-sensor data fusion[J].Proc. of IEEE,1997,85(1):pp.6-23.
[46] Van GenderenJ.L.,Pohl C.,Image fusion:Issues,techniques and applications,Intelligent Image Fusion, Proceedings EARSEL Workshop,Strasbourg, France, 1994,edited by Van Genderen.J.L and Cappellini.V, pp:18-26.
[47] Ehlers M., Multisensor image fusion techniques in remote sensing. Photogrammetric Engeneering and Remote Sensing.Vol.46, pp. 19-30,1991
[48]苗启广,王宝树,基于非负矩阵分解的多聚焦图像融合研究[J],光学学报,2005,25(6):755-759
[49] Waltz E.,and Llinas J. Multisensor Data Fusion.Boston:Artech House, 1990