Obtaining various tissues from microscopic of wood images has important significance for the analysis of wood properties

weather changes

and wood species

which relies on the results of image segmentation techniques. Level Set is conducted in the segmentation of wood images in our experiments described in this paper.After the combination of the edge-based and region-based models in Level Set

we introduce the local cues in image to improve the image segmentaion performance for the wood tissue's inhomogeneity and reduce the noise caused by the production of wood specimens. Then

an area threshold is used to get rid of blisters and other impurities in the image to obtain the wood pores at last. Experiments show that the proposed method can smoothly segment images of local non-uniform wood microstructure

and significantly reduced the noise.