Research on Segmentation and Recognition of Marrow Cells Image

Aiming at the characteristics of the marrow cell image, proposed a new method to check and measure local regularity and got a appropriate threshold using multi-fractal spectrum meanwhile accurate edges of different kinds of cells can be detected. Using Principal Component Analysis based neural network (GHA) to acquire three principal components and using Simulated Annealing (SA) and BP network to classify and recognize the marrow cells.