Advertisement

Journal of Optics

, Volume 43, Issue 1, pp 48–61 | Cite as

Hybrid DDCT-PCA based multi sensor image fusion

  • V. P. S. NaiduEmail author
Research Article

Abstract

Multi sensor image fusion algorithm based on directional Discrete Cosine Transform (DDCT) - Principal Component Analysis (PCA) hybrid technique has been developed and evaluated. The input images were divided into non-overlapping square blocks and the fusion process was carried out on the corresponding blocks. The algorithm works in two stages. In first stage, modes 0 to 8 were performed on images to be fused. For each mode, the coefficients from the images to be fused are used in the fusion process. The same procedure is repeated for other modes. Three different fusion rules are used in fusion process viz., 1. Averaging the corresponding coefficients (DDCTav), 2. Choosing the corresponding frequency band with maximum energy (DDCTek) and 3. Choosing the corresponding coefficient with maximum absolute value (DDCTmx) between the images. After this stage, there are eight fused images, one from each mode. In second stage, these eight fused images are fused using PCA. Performance of these algorithms were compared using fusion quality evaluation metrics such as root mean square error (RMSE), quality index (QI), spatial frequency and fusion quality index (FQI). It was concluded from the results that DDCTav performs poor and DDCTek performs slightly better than DDCTmx. Moreover, DDCTek is computationally simple and easily implementable on target hardware. Matlab code has been provided for better understanding.

Keywords

Principal component analysis Image processing Directional discrete cosine transform Multi sensor image fusion 

Nomenclature:

2D

Two Dimensional

Cov

Covariance function

DCT

Discrete Cosine Transform

DDCT

Directional Discrete Cosine Transform

FQI

Fusion Quality Index

HVS

Human Visual System

MSIF

Multi Sensor Image Fusion

PCA

Principal Component Analysis

QI

Quality Index

RMSE

Root Mean Square Error

SF

Spatial Frequency

References

  1. 1.
    V.P.S. Naidu, J.R. Raol, Pixel-Level Image Fusion using Wavelets and Principal Component Analysis – A Comparative Analysis. Def Sci J 58(3), 338–352 (2008)Google Scholar
  2. 2.
    V.P.S. Naidu, J.R. Raol, Fusion of Out Of Focus Images using Principal Component Analysis and Spatial Frequency. Journal of Aerospace Sciences and Technologies 60(3), 216–225 (2008)Google Scholar
  3. 3.
    V.P.S. Naidu, Discrete Cosine Transform-based Image Fusion”, Special Issue on Mobile Intelligent Autonomous System. Def Sci J 60(1), 48–54 (2010)CrossRefGoogle Scholar
  4. 4.
    B. Zeng and J.-J. Fu, “Directional discrete cosine transforms for image coding,” in Proc. of IEEE ICME-2006, pp.721–724, July 2006, Toronto, Canada.Google Scholar
  5. 5.
    Bing Zeng, Member, IEEE, and Jingjing Fu, “Directional Discrete Cosine Transforms—A New Framework for Image Coding”, IEEE Transactions on Circuits and Systems for Video technology, Vol. 18, No. 3, March 2008.Google Scholar
  6. 6.
  7. 7.
    Q. Sun, J. Tang, A New Contrast Measure based Image Enhancement Algorithm in the DCT Domain. IEEE Systems Man and Cybernatics 3, 2055–2058 (2003)Google Scholar
  8. 8.
    VPS Naidu, Girija G. and J. R. Raol “Evaluation of data association and fusion algorithms for tracking in the presence of measurement loss”, AIAA international Conference on Navigation, Guidance and Control, Austin, USA, August-2003.Google Scholar
  9. 9.
    Z. Wang, A.C. Bovik, A universal image quality index. IEEE Signal Proc. Letters 9(9), 81–84 (March 2002)Google Scholar
  10. 10.
    S. Li, J.T. Kwok, Y. Wang, Combination of Images with Diverse Focuses using the Spatial Frequency. Information Fusion 2, 169–176 (2001)CrossRefGoogle Scholar
  11. 11.
    Gemma Piella and Henk Heijmans, “A New Quality Metric for Image Fusion”, Proc. IEEE International Conference on Image Processing, Barcelona, Spain, pp173-176, 2003. Google Scholar
  12. 12.
  13. 13.

Copyright information

© Optical Society of India 2013

Authors and Affiliations

  1. 1.Multi Sensor Data Fusion LabCSIR-National Aerospace LaboratoriesBangaloreIndia

Personalised recommendations