Improved neural networks based method for infrared focal plane arrays nonuniformity correction

  • Authors:

  • Dongjie Tan;An Zhang

  • Affiliations:

  • School of Electronics and Information, Northwestern Polytechnical University, Xi'an, China;School of Electronics and Information, Northwestern Polytechnical University, Xi'an, China

  • Venue:
  • AICI'12 Proceedings of the 4th international conference on Artificial Intelligence and Computational Intelligence
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

The non-uniform response in infrared focal plane array (IRFPA) detectors produces corrupted images with a fixed pattern noise. In this study, an improved neural networks based method for nonuniformity correction (NUC) is presented. In the improved method, the correction process of neural networks is decomposed from one step to two steps to fine the correction results. Besides, it uses a local median value of each neuron's output as the desired output for each neuron. Experimental results show that the improved algorithm can eliminate fixed stripe noise and stochastic noise in raw images and make infrared images more slippery.