RBC Image Segmentation Based on Shape Reconstruction and Multi-scale Surface Fitting

The shape deformability of Red Blood Cell plays an important role in blood filterability. This paper proposed a combined approach for complex surface segmentation of Red Blood Cell. Firstly the individual cell was extracted using contour guiding method. Each pixel´s shading variation information was then used for 3D shape reconstruction. The recovered depth map of each image contributed to segment the shape through multi-scale surface fitting. The experimental result shown good results and obtained high classification accuracy.