Abstract-We present a method for segmenting 2D microscopy images of freshwater green microalgae. Our approach is based on a specialized level set method, leading to efficient and highly accurate algae segmentation. The level set formulation of our problem allows us to generate an algae's boundary curve as the result of an evolving level curve, based on computed background and algae regions in a given image. By characterizing the distributions of image intensity values in local regions, we are able to automatically classify image regions into background and algae regions. We present results obtained with our method. These results are very promising as they document that we can achieve highly accurate algae segmentations when comparing ours against manually segmented images (segmented by an expert biologist) and with results derived by other approaches covered in the literature.
Trichodesmium is a typical planktic genus in which trichomes are disposed either in fascicles or radially in rounded colonies. Based on morphological studies, there are eleven species of Trichodesmium, out of which nine are from marine environments and only two from freshwaters. Trichodesmium is mainly known for its capacity to form blooms and produce toxins in marine tropical and subtropical environments. There is no information about the capacity of the freshwater Trichodesmium species to produce toxins. It was only with molecular studies that the taxonomy of marine Trichodesmium started to be solved. However, up to now, no material has been available for molecular analyses of freshwater species. During the studies of microalgae from São Paulo state, a population resembling Trichodesmium was found in a recreational pond. The analyzed organisms formed fascicles of homocyted and not attenuated trichomes and cells with gas vesicles, a set of features that makes them different from the other freshwater Trichodesmium species. Thus, we have described the species Trichodesmium brasiliense sp. nov. based on material from Brazilian inland water. Also, we have suggested revision of some Brazilian literature citations of T. lacustre and their inclusion in the synonym of this new species.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.