A NEW SELF-ORGANIZATION CLASSIFICATION ALGORITHM FOR REMOTE-SENSING IMAGES

This paper presents a new self-organization classification algorithm f or remote-sensing images. Kohonen and other scholars have proposed sel f-organization algorithms. Kohonen's model easily converges to the loc al minimum by tuning the elaborate parameters. In addition to others, S.C. Amatur and Y. Takefuji have also proposed self-organization algor ithm model. In their algorithm, the maximum neuron model(winner-take-a ll neuron model) is used where the parameter-tuning is not needed. The algorithm is able to shorten the computation time without a burden on the parameter-tuning. However, their model has a tendency to converge to the local minimum easily. To remove these obstacles produced by th e two algorithms, we have proposed a new self-organization algorithm w here these two algorithms are fused such that the advantages of the tw o algorithms are combined. The number of required neurons is the numbe r of pixels multiplied by the number of clusters. The algorithm is com posed of two stages: in the first stage we use the maximum self-organi zation algorithm until the state of the system converges to the local- minimum, then, the Kohonen self-organization algorithm is used in the last stage in order to improve the solution quality by escaping from t he local minimum of the first stage. We have simulated a LANDSAT-TM im age data with 500 pixel x 100 pixel image and 8-bit gray scaled. The r esults justifies all our claims to the proposed algorithm.