Comparative Study on Infrared Image De-noising Based on Matlab - Intelligent Computing for Sustainable Energy and Environment - page 74

SSS J

Fig. 8. Different de-noising methods for the three noises

treated as the useful component details of the original image are remained during
the decomposition of the wavelet.So we can take the wavelet threshold combined
with histogram equalization to process the infrared images with Gaussian and
multiplicative noises, and take the multi-image average de-noising algorithm to
process the infrared images with salt & pepper noise, this is the better choice.

4 Conclusions

Image de-noising is a process technology to showing advantages and disadvan-
tages of each algorithm, contrasting of the linear theories in spatial domain and
favorite image de- noising algorithms based on the image visual effects. This
paper studies on the infrared application environments of different algorithms,
which prompts us to explore the new image theory and method of de-noising
algorithms, in order to eliminate noises in the images rapidly and effectively and
make them more clear for research and visual need, and study how to elimi-
nate the disturbing information of the image by filtering in order to satisfy one
frequency domain.

Acknowledgments. This work was financially supported by the National Nat-
ural Science Foundation of China (No.61178066) and Natural Science Foundation
of Heilongjiang (No.F201013).

References

1. Kang, Z.L., Xu, L.J.: An Algorithm Study on Infrared Image De-noising Based on
Wavelet Transform. Computer Simulation 28, 256-367+274 (2011)
2. He, Y.J., Li, M., Lv, D., Huang, K.: Novel Infrared Image De-noising Method Based
on Curvelet Transform. Computer Engineering and Applications 47, 191-193 (2011)