Annotation of image segments with ontologies (AISO)

TitleAnnotation of image segments with ontologies (AISO)
Publication TypeThesis
Year of Publication2013
AuthorsLingutla NTV
DegreeMaster of Science (M.S.) in Computer Science
UniversityOregon State University
CityCorvallis
Thesis TypemastersMaster’s
Abstract

This M.S thesis presents an interactive software tool that I have developed in the course of the past two years. This interactive tool is called AISO. AISO is aimed at interactive image segmentation and annotation tool designed to allow users to segment an image – such as those produced with digital photography or from scanned prints – and then annotate those segments with ontology terms. Many photo-editing and illustration soft- ware packages enable the ad-hoc editing of an image, but any highlighting and labeling utility requires thorough knowledge of the softwares illustration capabilities (i.e. layering, boundary detection) and does not include the structured integration of scientific data. For example, any labels applied to hand-illustrated segments super-imposed onto an image would have to be individually constructed and associated with a particular portion of an image. AISO simplifies this functionality and requires only a few input gestures and clicks to identify and label segments. The resulting structured image and ontology data allows for consistent extraction techniques. Researchers are thus empowered to construct meaningful image data sets drawn from their laboratories, online image archives, and publications. For this thesis I evaluated AISO by soliciting feedback from a selected group of biological researchers. They provided overall positive feedback on user friendliness, consistency and predictability of AISO, speed of interaction of AISO. As the key contribution, this thesis provides the first open source software for plant biologists by integrating the state-of-the-art image segmentation algorithms with plant ontology webservice. Based on our preliminary user study, AISO has potential to significantly advance current practices in plant biology research.

URLhttp://hdl.handle.net/1957/42883