Entropy Based ROI Extraction and Modified Contour Model for Image Segmentation

Segmentation process of an Image, represents meaningful way for further analysis and use in medical imaging, remote sensing and military objects detection. Due to poor resolution, segmentation become complex especially is an image is blurred or mixed pixels. Active contour technique is popular to get smooth curve around the boundary of 2D images but due to image gradient this techniques is unable to detect the boundaries of an objects. In this paper, first to calculate the entropy threshold based method to find the region of interest, then further contour model was applied to extract the efficient external features. Using this method we have extracted external features of an image, while traditionally only internals feature was able to extract. From the results it has revealed that after comparing traditional and proposed method of segmentation we get more enhanced and accurate results.