Publications

The field of computer vision has experienced much progress in the last two decades. Image analysis of photography  and  video  has  moved  out  of  computer  science research labs and into a wide range of applications. One example of progress in image analysis concerns the segmentation  of  images  on  the  basis  of  gray  scale,  color  hue, texture, geometry, and other features. Such image segmentation  allows  for  increasingly  refined  classification  of images and their components. In a parallel development, semantic  computing  has  pursued  the  creation  of  ontologies  in hopes of capturing and defining what it is we “know” about the world,  and presenting  it  in  the  form  of  a  terminology  network connected by defined relationships. This knowledge network is computable,  and  makes  it  possible  to  make  logical  inferences about facts and data annotated with ontology terms. By  combining  these  two  innovations:  image  analysis  and ontology  annotation,  we  can  imbue  images  with  structured meaning  and  enable  the  inferential  computability  of  image data. For example, it may be possible to segment an image of a plant  leaf  into  diseased  and  undiseased  tissue,  and  then  to annotate  these  segments  with  ontology  terms  describing  the disease  state  and  associated  phenotypes.  Once  a  database  of such images is developed, machine-learning algorithms can be applied to the data and predictive models can be developed. In this scenario, new images of plant leaves may be “tagged” with a disease state based on earlier examples. We have already explored the segmentation and ontological annotation  components  in  the  desktop  application  AISO  [1], but  would  like  to  see  this  functionality  available  in  an  online format  that  allows  for  better  processing  scalability,  storage, security,  and  collaborative  feature  sharing.  We  also  want  to apply machine learning to a collection of segmented, annotated images, thereby automating future image processing.