期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2014
卷号：62
期号：1
出版社：Journal of Theoretical and Applied
摘要：For managing data in a smart card�s limited memory, containing medical and biometric images, images compression is resorted to. For image retrieval, it is necessary that the classification algorithm be efficient to search and locate the image in a compressed domain. This study proposes a novel training algorithm for Multi-Layer Perceptron Neural Network (MLP-NN) to classify compressed images. MLP-NN is used for image classification. The most common training algorithm is Error Back Propagation algorithm (EBP) with a very poor convergence rate. Other second order approaches including Levenberg-Marquardt method and conjugate gradient method are better to train neural networks. This study proposes an improved training algorithm based on Levenberg-Marquardt method for Neural Network.
