Advertisement

Deblurring Image Using Motion Sensor and SOM Neural Network

  • Chu-Hui Lee
  • Yong-Jin Zhuo
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 513)

Abstract

As multimedia image related devices are widely used by the general public, multimedia image processing technology is more and more advanced, however there are still some problems that are worth to be explored and improved. How to deblurring an image without the information of speed and direction of moving objects is still a well-known ill-posed problem. In this paper, we proposed a system to deblurring image that can estimate important parameter advance to reduce the complexity of deblurring process. The data of sensor of moving object is collected. The SOM neural network is used to train to classify the speed and direction of the object from the sensor data. After that, we can estimate the speed and direction of objects without other algorithms. With such important parameters, deblurring processing will more efficient.

Keywords

Motion deblurring SOM neural network Notion sensor 

Notes

Acknowledgements

This research was supported by the Ministry of Science and Technology of Taiwan under Grant MOST-106-2221-E-324-023-.

References

  1. 1.
    Couzinié-Devy F, Sun J, Alahari K, Ponce J (2013) Learning to estimate and remove non-uniform image blur. In: IEEE conference on computer vision and pattern recognition, 1075–1082.  https://doi.org/10.1109/cvpr.2013.143
  2. 2.
    Oliveira JP, Figueiredo MAT, Bioucas-Dias JM (2014) Parametric blur estimation for blind restoration of natural images: linear motion and out-of-focus. IEEE Trans Image Process 23:466–477.  https://doi.org/10.1109/TIP.2013.2286328MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Arthur J, Attarian A, Hamilton F, Tran H (2018) Nonlinear Kalman filtering for censored observations. Appl Math Comput 316:155–166Google Scholar
  4. 4.
    Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biol Cybern 43:59–69MathSciNetCrossRefGoogle Scholar
  5. 5.
    Cheung YM, Law LT (2007) Rival model penalized self-organizing map. IEEE Trans Neural Netw 18:289–295.  https://doi.org/10.1109/TNN.2006.885039CrossRefGoogle Scholar
  6. 6.
    Wen CY, Lee CH (2002) Point spread functions and their applications to forensic image restoration. Forensic Sci J 1:15–26Google Scholar
  7. 7.
    Lee JM, Lee JH, Park KT, Moon YS (2013) Image deblurring based on the estimation of PSF parameters and the post-processing. Optik 124:2224–2224CrossRefGoogle Scholar
  8. 8.
    Dash R, Majhi B (2014) Motion blur parameters estimation for image restoration. Optik 125:1634–1640CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Information ManagementChaoyang University of TechnologyTaipeiRepublic of China

Personalised recommendations