An accurate segmentation method for white blood cell images

A part of our research work on an Automated Cell Count project is described. A major requirement for this project is an efficient method to segment cell images. This work presents an accurate segmentation method for an automatic count of white blood cells. First a simple thresholding approach is applied to give initial labels to pixels in the blood cell images. The algorithm is based on priori information about blood smear images. Then the labels are adjusted with a shape detection method based on large regional context information to produce meaningful results. This approach makes use of knowledge of the blood cell structure. The experimental result shows that this method is more powerful than traditional methods that use only local context information. It can perform accurate segmentation of white blood cells even if they have unsharp boundaries.