One Improved Watershed Transform for Medical Image Segmentation
As a classic image segmentation method, watershed algorithm is widely used. But the over-segmentation and sensitivity to noise are its drawbacks, many improved watershed methods have been developed to solve these problems. This paper presented an improved watershed algorithm for medical image segmentation. Firstly, an iterative data-adaptive Gaussian smoother is used to smooth large scale details while suppress noises. Secondly, the contour information of the original image is enhanced and revised by fusing the gradient with the detected edges. Finally, valleyfilling techenique is used to control the number of the resultant watersheded regions. The experiments have been done on the medical images and the results demonstrated the effectiveness of the proposed method.
image segmentation watershed Image fusion valley-filling iteration data-adaptive Gaussian smoother edge detection
Wei Hao Sheng Zheng Shuzhi Ye
College of Electrical and New Energy Institute of Intelligent Vision and Image Information, China Th College of Computer and Information Institute of Intelligent Vision and Image Information, China Thr
国际会议
太原
英文
594-598
2010-10-22（万方平台首次上网日期，不代表论文的发表时间）