Total views : 171

A robust technique for image mosaicing using modified SIFT


  • School of Electronics Engineering, Lovely Professional University, Phagwara, Punjab, India


In this paper a robust technique is used for image mosaicing to reduce the computational time and increase the efficiency through modified Scale Invariant Feature Transform SIFT. Modified Scale Invariant Feature Transform algorithm is used to increase the efficiency and to reduce the computational time. In this normalized cross correlation is used to find the best possible match for the image warping. Area found by Normalized Cross Correlation is used for feature matching, through this method computational time is reduced. Two different methods are combined to get the best output. As the number of matches increased the efficiency of the algorithm also increased. The area for matching is reduced so the computational time gets reduced. The output mosaicked image is warped by the best possible matches This paper depicts the implementation of the real images click by a normal Samsung phone camera at different angles and locations. Homography is used to find the angular relation between the images. Normalized Modified SIFT algorithm is used to increase the efficiency and reduce the computational time. Mosaiced image is efficient enough as compare to SIFT algorithm.


Computational Time, Efficiency, Image Mosaicing, Modified Scale Invariant Feature Transform (SIFT) Algorithm, Normalized Cross Correlation.

Full Text:

 |  (PDF views: 169)


  • Shmuel P, Joshua H. Panoramic Mosaics Manifold Projection. IEEE Trans. on Panoramic Mosaicing. 1997, p.338-43.
  • Yining D, Tong Z. Generating panorama photos, HewlettPackard Labs.
  • Seong H, Hyung K, Sang L, Nam C, Soo K. Panorama mosaic optimization for mobile camera systems. IEEE Trans. on Panorama, 2007.
  • Alex R, Glora E, Shmuel P. Minimal Aspect Distortion mosaicing of long scenes. Springer, 22 November 2007, 187-206.
  • Lin Z, Shengping Z, Junn Z, Yunhu Z. Dynamic image mosaic via sift and dynamic programming. Springer, 19 September 2013.
  • Zezzhong X. Consistent image alignment for video mosaicing.Springer. 16 February 2011, 129-35.
  • Akifumi I. Image mosaicing: create high quality panoramic multi spectral image. 12 February 2002.
  • Lin J, Wang Y, Liang H. Image mosaic based on simplified SIFT”IERI, 2012, v.10.
  • Pengrui Q, Ying L, Hui R. Image mosaics algorithm based on SIFT feature point matching and transformation parameters automatically recognizing. Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013), 2013. Doi:10.2991/ iccsee.2013.392
  • Yoav S, Shree N. Generalized mosaicing: high dynamic range in a wide field of view. International Journal of Computer Vision. 2003 Jan; 28:245-67.
  • Matthew Brown, David G. Lowe. Recognising Panoramas.Department of Computer Science, University of British Columbia. International Conference on Computer Vision (ICCV 2003), Nice, France, 2003 Oct, p. 1218-25
  • Xingxing S, Wenxing B. The remote sensing image matching algorithm based on the normalized cross-correlation and SIFT. Springer. 10 December 2013, p. 417-22.
  • David G. Lowe. Object recognition from local scale-invariant features. Department of Computer Science, University of British Columbia. Proc. of the International Conference on Computer Vision, Corfu, 1999 Sept, p. 1-8.
  • Matthew Brown, David G. Lowe. Automatic panoramic image stitching using invariant features. Department of Computer Science, University of British Columbia.International Journal of Computer Vision. 2007 Aug; 74(1):59-73
  • Sai Venu PK, Jilani SAK, Ramana Reddy P.. A Real-Time Image Mosaicing using Scale Invariant Feature Transform.Indian Journal of Science and Technology. 2016 Mar; 9(12).DOI: 10.17485/ijst/2016/v9i12/88175.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.