The research of classification algorithm based on fuzzy clustering and neural network

Abstract

The algorithms for remote sensing image classification can be cataloged into classic classification, fuzzy classification, and neural network classification. For classic classification algorithm, the space distribution of data features should be assumed, and it is difficult to put in expert knowledge to remote sensing information. As to fuzzy classification algorithm, the meaning of the subordinate degree is not definite. In regard to neural network classification algorithm, network framework parameters are difficult to decide, training time is long, and the neural network tends to fall into local optimization situation. A modified Fuzzy-ISODATA algorithm and BP neural network algorithm was developed in this paper. The integration of two algorithms was applied in remote sensing classification. A comparison of classification accuracy, speed and practicability for each algorithm was made based on the same train sampling area. The experiment was conducted in Shunyi, Beijing, China (40°00 minutes-40°18 minutes, 116°28 minutes-116°58 minutes, which covers a total area of 1021 km2, with 45 km long from east to west and 30 km long from north to south)with TM image. The result indicates that the accuracy of integration classification algorithm increases compared with simple fuzzy clustering algorithm and simple neural network algorithm in Shunyi area, but the speed should be improved.