The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B5. Beijing 2008 
Method 
Effect 
Time Complexity 
MCT 
Good. A few serious 
displacements in the 
panorama. 
0(n2) 
SPST 
Better. No obvious 
displacement but 
some minor blurries in 
the panorama. 
0(n3) 
MRCT 
Best. No obvious 
displacement and few 
minor blurries in the 
panorama. 
0(n 2 * cei,{2lE) - 2 )to 
construct a (1+e) 
approximate MRCT 
Table 1. Comparison of Four Mosaicing Methods 
5. CONCLUSION 
Because of limitation of the apparatus, in fields of medicine and 
LSI etc, microscope images of the target are gathered in many 
frames and should be mosaiced to construct the panorama. The 
amount of the microscope images is large and existing methods 
can not deal with the accumulated errors well. In this paper, the 
method based on graph theory is provided and several 
approaches based on spanning trees are compared, including 
minimum cost spanning tree, shortest path spanning tree with 
media as root and minimum routing cost spanning tree, which 
takes the registration results based on spatial relationships as the 
weights of the mosaicing graph. The experiments show that the 
methods based on spanning trees of mosaicing graph is much 
better than the method based on local registration. According to 
the comparison, the mosaicing method based on SPST as root 
and MRCT are appropriate to construct high quality microscope 
panorama, between which the latter is a little better but 
consumes much time, while the method based on SPST is more 
efficient than the method based on MRCT. Therefore, the 
method based on SPST is much proper to construct panorama 
with large scale microscope images and high quality. 
For microscope images mosaicing, an improvement depends on 
the algorithm of the Adjacent-Vertex-in-Graph Minimum 
Routing Cost Spanning Tree, which will construct the panorama 
with less error. 
REFERENCES 
Bamea, D. I., and Silverman, H. F., 1972. A class of algorithms 
for fast digital registration. IEEE Transactions on Computer, vol. 
c-21, pp. 179-186. 
Brown, L. G., 1992. A survey of image registration techniques. 
ACM Computing Surveys, vol. 24, pp. 325 - 376 
Chen, S. E., 1995. QuickTime VR : an image-based approach to 
virtual environment navigation, in Proceedings of the 22nd 
annual conference on Computer graphics and interactive 
techniques, Los Angeles, CA, USA, pp. 29 -38. 
Choe, T. E., Cohen, I., Lee, M., and Medioni, G., 2006. Optimal 
global mosaic generation from retinal images. In 18th 
International Conference on Pattern Recognition(ICPR 2006), 
Hong Kong, China, pp. 681 - 684. 
Cormen, T. H., Leiserson, C. E., Rivest, R. L., and Stein, C., 
2001. Introduction to Algorithms, Second Edition. Cambridge , 
Massachusetts London, England: The MIT Press. 
Davis, J., 1998. Mosaics of scenes with moving objects, in 
IEEE Computer Society Conference on Computer Vision and 
Pattern Recognition, Santa Barbara, California, USA, pp. 354 - 
360. 
Garey, M. R., and Johnson, D. S.,. Computer And Intractability: 
A Guide To The Theory Of NP-Completeness. New York, USA: 
Freeman, 1979. 
Gledhill, D., Tian, G. Y., Taylor, D., and Clarke, D., 2003. 
Panoramic imaging—a review. Computers & Graphics, vol. 27, 
pp. 435-445. 
Gong, Yong- xi., Liu, Yu., Xie, Yu-bo., et al. Image registration 
algorithm based on blocking-spatial clustering .Computer 
Engineering and Applications, 2007, 43( 29): 53- 55. 
Hsu, S., Sawhney, H. S., and Kumar, R., 2002. Automated 
mosaics via topology inference. IEEE Computer Graphics and 
Applications, vol. 22, pp. 44 - 54. 
Kang, E.-Y., Cohen, I., and Medioni, G., 2000. A graph-based 
global registration for 2D mosaics. In Proceedings of the 15th 
International Conference on Pattern Recognition, Barcelrona, 
Spain, p. 257-260. 
Kang, S. B., and Weiss, R., 1999. Characterization of errors in 
compositing panoramic images. Computer Vision and Image 
Understanding, vol. 73, pp. 269-280. 
Kim, D.-H., Yoon, Y.-I., and Choi, J.-S., 2003. An efficient 
method to build panoramic image mosaics. Pattern Recognition 
Letters, vol. 24, pp. 2421-2429. 
Manjunath, B. S., Shekhar, C., and Chellappa, R., 1996. A new 
approach to image feature detection with applications. Pattern 
Recognition, vol. 29, pp. 627-640. 
Marzotto, R., Fusiello, A., and Murino, V., 2004. High 
resolution video mosaicing with global alignment. In 
Proceedings of the 2004 IEEE Computer Society Conference on 
Computer Vision and Pattern Recognition, Washington, DC, 
USA, pp. 692-698. 
McLauchlan, P. F., and Jaenicke, A., 2002. Image mosaicing 
using sequential bundle adjustment. Image and Vision 
Computing, vol. 20, pp. 751-759. 
Meijering, E. H. W., Zuiderveld, K. J., and Viergever, M. A., 
1999. Image reconstruction by convolution with symmetrical 
piecewise nth-order polynomial kernels. IEEE Transactions on 
Image Processing, vol. 8, pp. 192-201. 
Nikolaidis, N., and Pitas, I., 2005. Computationally efficient 
Image mosaicing using spanning tree representations. In 
Proceedings of the 10th Panhellenic Conference on Informatics, 
Volas, Greece, p. 716-724. 
Park, J.-S., Chang, D.-H., and Park, S.-G., 2000. Automatic 
generation of photo-realistic mosaic image. In First IEEE 
International Workshop on Biologically Motivated Computer 
Vision,BMCV 2000, Seoul, Korea, pp. 321-334.