Wavelet image denoising based on fusion threshold functions
/ 0
- Details
- Category: Information technologies, systems analysis and administration
- Last Updated on 04 August 2016
- Published on 04 August 2016
- Hits: 3336
Authors:
Guoliang Sun, Rongcheng College of Harbin University of Science and Technology, Weihai, China
Abstract:
Purpose. Specific to the existing discontinuity and constant deviation in denoising of wavelet threshold function, this paper analysed the integrated denoising function of traditional wavelet threshold function.
Methodology. Through analysis of the defects of wavelet soft threshold function and hard threshold function and according to the characteristics of the traditional threshold function as well as the design idea and procedure, the paper establishes an integrated threshold function on the basis of the traditional threshold function and offers a simulation diagram extracted from the corresponding threshold function. Through the simulation diagram of the threshold function, it analyses the advantages of integrated threshold function.
Findings. According to the result, the integrated threshold function established on the basis of the characteristics and design idea of wavelet soft threshold function and hard threshold function integrates the advantages of traditional threshold functions, effectively overcoming the discontinuity of the hard threshold function and constant deviation of the soft threshold function.
Originality. Based on the structure and characteristics of the traditional wavelet threshold function, the article puts forward an idea how to combine the traditional wavelet threshold function and the fusion function which is not only used to transform the traditional threshold function, but also adds the fusion coefficient to modify it, which makes the fusion function adaptive.
Practical value. The results of the paper can effectively improve the denoising ability of an image, which apart from effective removal of image noise, reserves detailed information of images, laying solid foundation for in-depth processing of a high-quality image.
Список литературы / References
1. Mo X.Q. and He A., 2014. Engineering Image Processing Based on Adaptive Threshold Median Filtering Algorithm. Software Guide, No. 3, pp. 55–59.
2. Xu S.S., 2015. The Application of Improved Fuzzy C-Means Clustering Algorithm in Image Segmentation. Chang’an University.
3. Liu D.J., 2013. Research on Image Denoising Method in Image Edge Detection.Computer CD Software and Applications, No. 12, pp. 303–303.
4. Sun X.X. and Qu W., 2014. Comparison between Mean Filter and Median Filter Algorithm in Image DenoisingField”. Applied Mechanics & Materials, pp. 4112–4116.
5. Zhang X., Feng X. and Wang W., 2013. Gradient-based Wiener filter for image denoising. Computers & Electrical Engineering, Vol. 39, No. 3, pp. 934–944.
6. Li T.K., Liu H. and Wang, 2013. Self-adaptive Kalman Filter Algorithm Research Based on Wavelet Transform. Ordnance Industry Automation, No. 1, pp. 32–35.
7. Xing W.L. and Zhang B.H., 2014. An Improvement Based on Wavelet Transform Speech Denoising Threshold Function. Advanced Materials Research, pp. 828–832.
8. Hu Y.H., 2015. Compressed Sensing Image Denoising Method and its Application in Wireless Decay Channels. East China Jiaotong University.
 03_2016_Guoliang
|
|
 2016-07-29  1.28 MB  770 |
|
Archive