Precise segmentation of cleavage of the neuron stem cells in time lapse image sequences

To study the cleavage of neuron stem cells in time lapse image sequences and realize their features abstraction, identification and tracking, a precise segmentation algorithm that can preserve the shape of division cells is presented in this paper. The fuzzy threshold segmentation is based on Zadth's maximum entropy. The optimal parameters of the maximum fuzzy entropy are decided by genetic algorithm. Region merging and splitting of the under-segmentation objects of the result of fuzzy segmentation are realized by weighted distance transform, region labeling and some operations on morphology. By comparison with some results of fuzzy and hard segmentation, this algorithm can implement the precise segmentation that is necessary for some specified objects in automatic identification and tracking of neuron stem cells.