The Study of Non-uniformity Correction Algorithm for IRFPA Based on Neural Network

It is very important to study non-uniformity correction algorithm in infrared focal plane array (IRFPA). In order to improve the convergence speed and non-stability in traditional neural network non-uniformity correction algorithm, a new scene-based non-uniformity correction algorithm for IRFPA was designed in this paper. The algorithm firstly arrange a pixelpsilas gray value and its around eight pixelspsila gray value from small to big and compute the mid 5 valuespsila mean in this new sequence as the pixelpsilas new gray value. Then using a traditional neural network algorithm do a non-uniformity correction on the infrared image again. Besides, we try to use a new estimating algorithm to calculate precisely the scope of the convergence constant in iterative equations. Compared with the result of several algorithms, the new algorithm has better correction effect than other three algorithms, and gets faster convergence speed.