A Neural Network-Based Classification of Water Resource Images

Abstract

Image classification from a database is particularly flinty for traditional machine learning algorithms because of the large number of images and variety of details that describe an image. For these reasons, traditional machine are unstable to classify images from a database. Furthermore, these machines take long time for classification. One of the existing methods for recognition, classification and retrieval of images is based on Artificial Neural Networks (ANN). Neural Network is an information processing ideal that is inspired by the way biological nervous system, such as the brain, process information. In the proposed system, image classification is based on Back propagation neural network with one hidden layer. There hasn’t been any significant work for water resource classification. Hence, a need for robust algorithm with high classification accuracy is proposed in this paper.