Segmentation for Images of a Single Stem Cell Using Morphological Operations and Statistical Region Merging

For some images of a single stem cell, the boundary delineating the cell is discontinuous or blurry at some locations. If the statistical region merging (SRM) method is applied directly on such images, the image segmentation results may not be ideal. In this paper, for each such image, we add some gradient information into the image; then apply a discontinuous filter on the image so that the image is smoothed a bit and the edges of the image are kept well. Next, closing operations of morphology are applied on the filtered image; and the processed image is segmented using SRM. Finally, apply a threshold on the segmented image to obtain a binary image; apply a hole-filling function to the binary image; extract the biggest connected component in the hole-filled image; and apply a linear transform on the image of the biggest component to match the input image as well as possible in terms of the least squares fitting. This transformed image is the segmentation result. We have applied SRM using connectivity of 4 and 8 as well as a hexagonal lattice. The corresponding segmentation results are tabulated for convenient comparisons; and the results can show that the proposed method may be helpful for the segmentation of such images.