Classification for remote sensing image by vector-based neural network

The artificial neural network technique developing rapidly in recent years provides a new means for classification of remote sensing image. While a lot of neural network algorithms have some problems in practice and can't get satisfaction result. In this paper, Vector-based BP neural network algorithm in the classification is discussed. vector information plays an assistant decision-making role during the image classification. It will help to define the sample training data and be an effective tool to evaluate the classification result. A qualitative comparison demonstrates that both original images and the classified maps are visually well matched. A further quantitative analysis indicates that the accuracy of this algorithm is better than the result of the traditional BP approaches.