A variational approach to video segmentation for botanical data

In order to engage in photosynthesis, plant leaves absorb CO₂ via the opening of pores in their surfaces called stomata. Water evaporates through open stomata, however, which is a detriment to plant function. Thus a plant will seek a stomatal aperture that balances its need for CO₂ with its aversion to H₂O loss. In order to visualize a particular leaf's stomatal aperture, an experimentalist injects the leaf with dye so that it fluoresces. Regions with a higher relative intensity that do not correspond to veins in the leaf then correspond to areas in which the stomata are closed and the darker nonvein regions to areas in which the stomata are open. A camera is used to collect the emitted light, and a fluorescence pattern is measured. Images are continually recorded as these patterns change with time, resulting in a video sequence. The goal of this paper is to segment one such video sequence into fluorescing and nonfluorescing regions. After preprocessing the video, we take a variational approach to the segmentation problem and solve the associated three-dimensional evolution equation using a semi-implicit numerical scheme. A fixed-point formulation of the method is presented as are results of the segmentation for actual leaf data.