Medical Image Segmentation With Texture-Based Region Merging
Kaiyu Li · Computer Knowledge and Technology · 2011
The use of the watershed algorithm for image segmentation is widespread,because it is able to produce a complete division of the image.However,it is susceptible to over-segmentation and in medical image segmentation,this meant that the method is limited.In order to solve the over-segmentation problem produced by the watershed transform for image segmentation.We present a watershed segmentation method with haralick's Texture-Based Region Merging.The original image was preprocessed with Gaussian filter and Sobel filter,on which thresholding is performed to remove weak edge pixels.The normalized mutual information similarity measure we present as evaluation function applies to the similarity in textural features belonging to two neighboring partitions.Experimental results show that this method can effectively avoid over-segmentation of watershed algorithm and perfectly and accurately obtain the segmentation result of medical image.