An improved watershed segmentation using complex wavelets and modified level set method

In this paper we proposed a new image segmentation method that incorporates Dual tree complex wavelet transform (DT-CWT), Improved watershed algorithm and modified level set method. The watershed algorithm has been extensively employed for image segmentation problem. It is used to segment the target object from complex background. But for noisy images it leads to over- segmentation and under-segmentation problems. Complex wavelets are used to denoising the image. To solve the above over-segmentation and under-segmentation problem watershed transform was modified based on Wasserstein distance. The edge indicator function of the modified level set method was used to extract the boundaries of objects. The efficiency of the proposed algorithm is shown by experimenting on the noisy finger print images.