Abstract In this article, two new facial recognition techniques based on a single vector Decomposition (SVD). Here is the method of the principal component method (PCM) and linear vector discriminate (LVD) applied to the facial features, the main component of the detection face recognition problem. The human face is full of information, but it works all the information that is time-consuming and inefficient. Better,... In this article, two new facial recognition techniques based on a single vector Decomposition (SVD). Here is the method of the principal component method (PCM) and linear vector discriminate (LVD) applied to the facial features, the main component of the detection face recognition problem. The human face is full of information, but it works all the information that is time-consuming and inefficient. Better, special and important information and other information that is not useful that the system is an effective solution. The main component of the method aspects of face recognition. Vectors and face their own value calculated by a series of portraits. New faces projected onto the surface of the expanded clean room and a weighted sum of their face. The weights are used to detect the face. The Euclidian distance in time and space for growth in the face of this complexity using two singular value decomposition methods. The simulation results show that the effectiveness of the proposed faces recognition technology. Here is the face used principal component method and linear discriminate method series of special value. To Test, the data shows that the face of the proposed algorithm influences the complexity its accuracy. Basis, it is concluded that the major part of the flex can achieve good results than other methods. The results also realized that the time complexity of the proposed method significantly reduces promote the effective implementation of the proposed method. Read More Read Less

Abstract In order to suppress the noise adaptively while enhancing the image details, an adaptive image enhancement method based on genetic algorithm in Nonsubsampled Contourlet (NSCT) domain is proposed. The optimal parameters of the image enhancement function are obtained adaptively through genetic algorithm (GA). The NSCT high frequency sub-bands coefficients are processed by the image enhancement function, the coefficients which are less than the... In order to suppress the noise adaptively while enhancing the image details, an adaptive image enhancement method based on genetic algorithm in Nonsubsampled Contourlet (NSCT) domain is proposed. The optimal parameters of the image enhancement function are obtained adaptively through genetic algorithm (GA). The NSCT high frequency sub-bands coefficients are processed by the image enhancement function, the coefficients which are less than the low threshold are set to 0 and the coefficients between the low threshold and the high threshold are enhanced. Experimental results demonstrate that the proposed method can adaptively enhance the image details and suppress noise at the same time, the detail variance is significantly improved, and a better visual effect is obtained. The results processed by the proposed method are better than that by classical enhancement methods. Read More Read Less