Noise Characterization in Web Cameras using Independent Component Analysis

Authors

  • Mohammad Asmat Ullah Khan Department of Electrical and Computer Engineering Effat University Jeddah, Saudi Arabia
  • Tariq Mahmood Khan Department of Electrical Engineering COMSATS Institute of Information Technology, Islamabad, Pakistan.
  • Rabia Bahadar Khan Department of Electrical Engineering COMSATS Institute of Information Technology, Abbotabad, Pakistan.
  • Atiqa Kiyani Department of Electrical Engineering COMSATS Institute of Information Technology, Abbotabad, Pakistan
  • Muhammad Aurangzeb Khan Department of Electrical Engineering COMSATS Institute of Information Technology, Islamabad, Pakistan

Keywords:

fixed pattern noise, interaction noise, temporal noise, independent component analysis, principle component analysis

Abstract

An image captured by a web camera contains stationary and nonstationary noise patterns. These noise patterns are of three types i.e. Fixed Pattern Noise (FPN), Interactive Nose (IN) and Temporal Noise (TN). TN is an independent noise pattern and needs an algorithm that does exploit its higher-order dependencies. Previously, these noise patterns have been characterized using Principal Component Analysis (PCA). PCA is restricted to second order dependencies. In this paper Independent Component Analysis (ICA) has been investigated for actual TN noise. The experimental results demonstrates the effectiveness of the proposed method.

References

Jose Manuel, Lopez-Alonso, and Javier Alda, "Characterization of artfacts in fully digital mage-acquisition systems: Application to web cameras" in Society of Photo-Optical Instrumentation ngineers(SPIE), 2004, vol. 43, pp. 257-265.

Heli T. Hytti, "Characterization of digital image noise properties based on raw data" in mage Quality and System Performance III, 2006, vol. 6059, 60590A.

Tetsuya Takiguchi and Yasuo Ariki, "Pca-based speech enhancement for distorted speech ecognition" in Journal of multimedia, 2005, vol. 2, pp. 13-18.

M. Stewart Bartlett, Javier R. Movellan, and Terrence J. Sejnowski, "Face recognition by ndependent component analysis" in IEEE Transactions on Neural Networks, 2002, pp. 450-1464.

Bell A. J., T. J. Sejnowski, and Vision Res, "The independent components of natural scenes re edge filters," in In Neural Comput, 1997, vol. 37, pp. 3327-3338.

S. Makeig, A. J. Bell, T.-P. Jung, and T. J. Sejnowski, "What is the goal of sensory coding?" n In Neural Comput, 1994, vol. 6, pp. 559-601. http://dx.doi.org/10.1162/neco.1994.6.4.559

M. J. McKeown, S. Makeig, G. G. Brown, T.-P. Jung, S. S. Kindermann, A. J. Bell, and . J. Sejnowski, "Analysis of fmri by decomposition into independent spatial components" n Human Brain Mapping, 1998, vol. 6, pp. 160-188. http://dx.doi.org/10.1002/(SICI)1097-0193(1998)6:33.0.CO;2-1

Published

2014-09-20

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.