An Improvement of Two-Dimensional Maximum Entropy Thresholding Segmentation Algorithm for SAR Image

In allusion to complex land SAR images, a modified partition method for two dimensional maximum entropic thresholding method is proposed. In this algorithm, a weighted factor is introduced into the criterion function of detection threshold, which strengthen the adaptive capacity to complex land SAR images. Simultaneously, it also improves the accuracy of image segmentation and reduces the false alarm rate and missed alarm rate. Experimental results show that the modified method has better performance in image segmentation.