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

Yuyu Zhou1,2, Hong Chen3, Qijiang Zhu1
1Research Center for Remote Sensing, Department Geography and Beijing Key Laboratory for Remote Sensing of Environment and Digital Cities, Beijing Normal University, Beijing, China
2Beijing Normal University, Beijing, Beijing, CN
3Res. Center for Remote Sensing, Beijing Normal Univ., China

Tóm tắt

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. In the fuzzy classification algorithm, the meaning of the subordinate degree is not definite. In the neural network classification algorithm, network framework parameters are difficult to decide, training time is long, and the neural network tends to fall into a local optimization situation. A modified Fuzzy-ISODATA algorithm and a BP neural network algorithm have been developed. The integration of the two algorithms was applied to remote sensing classification. A comparison of classification accuracy, speed and practicability for each algorithm was made based on the same training sampling area. The experiment was conducted in Shunyi, Beijing, China (40/spl deg/00'-40/spl deg/18'N, 116/spl deg/28'-1161/spl deg/58'E, which covers a total area of 1021 km/sup 2/) with a TM image. The result indicates that the accuracy of integration classification algorithm increases compared with the simple fuzzy clustering algorithm and the simple neural network algorithm in the Shunyi area, but the speed should be improved.

Từ khóa

#Classification algorithms #Clustering algorithms #Fuzzy neural networks #Neural networks #Remote sensing #Multi-layer neural network #Image classification #Pixel #Geography #Cities and towns

Tài liệu tham khảo

10.1109/78.650090 miao, 2001, Remote Sensing classification based on fuzzy Gauss function neural network, Remote Sensing Technology and Application, 16, 62 warner, 1997, An evaluation of the potential for fuzzy classification of multispectral data using neural networks, PE & RS, 63, 1285 fang, 1997, Remote Sensing technique applied in geoscience—a review of its present development, GEOGRAPHICAL RESEARCH, 17, 96 zhu, 1992, Some key problems and deal method about applying fuzzy mathematic method, Fuzzy System and Mathematics, 6, 57 zhang, 2000, A new kind of combination rule of evidence theory, Control and Decision, 15, 540 fang, 2000, The research of data fusion from multiple sources by evidential reasoning, Journal of Remote Sensing, 4, 106 congalton, 1998, Mapping and monitoring agricultural crops and other land cover in the lower Colorado River Basin, PE & RS, 64, 1107 fisher, 1994, Visualization of the reliability in classified Remotely Sensed images, Photogrammetric Engineering and Remote Sensing, 60, 905 pu, 2000, Hyperspectral Remote Sensing and its application 10.1080/014311697218700 dreyer, 1993, Classification of land using optimized neural networks on SPOT data, PE & RS, 59, 617 civco, 1997, Artificial neural networks for land cover classification and mapping, INT J Geographical Information System, 18, 237 wang, 1999, A classification of Remote Sensing image using wavelet neural network, Journal of Image and Graphic, 4, 368 zhang, 1998, A fully fuzzy supervised classification of Remotely Sensed imagery, 23, 211 luo, 1999, Fuzzy clustering method with partial supervision and its application on remotely sensed classification, Remote Sensing Technology and Application, 14, 37 chen, 2000, Application of K-means classification in Remote Sensing, Infrared and Laser Engineering, 29, 26 wang, 1997, Artificial neural network models in Remote Sensing and multisource geographic data classification, Scientia Geographica Sinica, 17, 105