We attempt to study content-based image search, automatic learning-based linguistic indexing of pictures, and different ways to browse a large collection of images. The project was started in 1995. The current work focuses on three areas: (1) developing highly efficient machine learning mechanisms for imagery data, (2) developing models for high-dimensional imagery, and (3) developing a learning-based image annotation and retrieval system. Besides modeling objects and concepts in images, we also consider aesthetics, composition, and emotions. . . . more >>>
This research project will advance information technologies related to biological imaging, medical imaging, and genomic databases. The research group is currently collaborating with Professors Anderson and Puri's groups to advance understanding of stomatal guard cell walls through imaging. A previous effort of the group was the SHIRAZ project, jointly with the Cheng lab in the Pathology Department of Penn State.
Many are concerned about climate change and one of the most important climate research problems is understanding the relationship between oceans and the global climate. A significant challenge facing climatologists and meteorologists today is making sense of the vast and continually increasing amount of data generated by earth observation satellites, radars, and sensor networks. These data are increasingly available in high-resolution image formats and must be incorporated correctly into climate change models. . . . more >>>
This collaborative research project aims at advancing information technologies related to the preservation, retrieval, analysis, and dissemination of digital imagery for art and cultural heritages. We have studied Asian paintings and European paintings (in particular those of Vincent van Gogh). . . . more >>>
This research project aims at advancing technologies related to the filtering of images. We developed one of the first image-based filter for online objectionable contents, back in 1997. The project also studies image-based CAPTCHAs for the discrimination between robotic and human users on the Internet. . . . more >>>