International Journal of Engineering and Technology

In this paper, an unsupervised change detection technique of multispectral images based on wavelet fusion and Kohonen Clustering Network is presented. The proposed method fuses absolute difference and change vector analysis image using wavelet fusion rules. The fused image highlights the changed areas while suppress unchanged areas. The Kohonen clustering network is used to create the final change map with changed areas highlighted. The performance of the proposed method was tested on two Landsat 5 TM images of Alaska region. The results obtained were compared with some other existing state of the art methods and it is observed that the proposed method outperforms the other methods.