No abstract

Based on the complexity and randomness of the infrared image degradation factors, and integrates the strong de-noising features of multi-scale morphological wavelet and the salient problem solving features of Hopfield neural network in optimization, this paper presents a new algorithm for infrared degraded image restoration. The algorithm takes advantage of the continuous recycle between "multi-scale morphological wavelet de-noising" and "Hopfield neural network iteration" so as to makes access to a better recovery of infrared images. The algorithm also solves the problems in noise suppression and image detail protection of traditional Hopfield neural network image restoration algorithm and successfully protects the edge of the recovery images and details. Simulation results prove the effectiveness of the recovery algorithm.

No abstract

No abstract

This article realized a method applying Haar features to train Adaboost classifier, and combined skin and lip color separation algorithm to form a self-adaptive skin and lip color separation model, which can dynamically adjust constant parameters of skin and lip separation algorithm based on the result of applying Haar features to train Adaboost classifier. The model can dynamically acquire distribution range of skin color and lip color, and improve the effectiveness and robustness of lip reading deletion. Applying the method to deal with 4000 image in GENKI database, it successfully detected lip area and had the smaller deviation. Lastly, curve fitting for the edge of the lip region was made to locate lip. The results showed that the method was more effective.