The striping pattern nonuniformity of the infrared line scanner (IRLS) severely limits the system performance. An adaptive nonuniformity correction (NUC) algorithm for IRLS using neural network is proposed. It uses a one-dimensional median filter to generate ideal output of network and can complete NUC by a single frame with a high correction level. Applications to both simulated and real infrared images show that algorithm can obtain a satisfactory result with low complexity, no need of scene diversity or global motion between consecutive frames. It has the potential to realize real-time hardware-based applications.

By using orthogonal discrete wavelet transform (ODWT) and generalized cross validation(GCV),and combining with Luck-Richardson algorithm based on Poisson-Markov model(MPML),several new super-resolution image restoration algorithm are proposed. According to simulation experiments for practical images, all the proposed algorithm could retain image details better than MPML, and be more suitable to low signal-to-noise ratio (SNR)images. The single operation wavelet MPML(SW-MPML) algorithm and MPML algorithm based on single operation wavelet transform(MPML-SW) avoid the iterative operation of self-adaptive parameter in MPML particularly, and improve operating speed and precision. They are instantancous to super-resolution image restoration process and have extensive application foreground.