This paper provides a bioimage informatics system of detecting and tracking protein molecules, called APP-GFPs, in a live-cell video captured by a fluorescent microscope. Since both processes encounter many difficulties such as many targets, less appearance information, and heavy background noise, we will try to design the system as robust as possible. Specifically, for the detection, a machine learning-based method is employed. For tracking, a method based on a global optimization strategy is newly developed. Experimental results showed that the speed and direction distributions of molecular motion by the proposed system were very similar to that by manual inspection.
At the current rate of technological advancement and social acceptance thereof, it will not be long before wearable devices will be common that constantly record the field of view of the user. We introduce a new database of image sequences, taken with a first person view camera, of realistic, everyday scenes. As a distinguishing feature, we manually transcribed the scene text of each image. This way, sophisticated OCR algorithms can be simulated that can help in the recognition of the location and the activity. To test this hypothesis, we performed a set of experiments using visual features, textual features, and a combination of both. We demonstrate that, although not very powerful when considered alone, the textual information improves the overall recognition rates.
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.