Abstract:

The need for efficient content-based image retrieval has increased tremendously in many application areas such as biomedicine, military, commerce, education, Web image classification and searching, and social networking.  Automated annotation of digital pictures has been a highly challenging problem for computer scientists since the invention of computers. The capability of annotating pictures by computers can lead to breakthroughs in a wide range of applications.  In our work, by advancing statistical modeling and optimization techniques, we can train computers about hundreds of semantic concepts using example pictures from each concept. The ALIPR (Automatic Linguistic Indexing of Pictures - Real Time) system of automatic and high-speed annotation for online pictures has been constructed.  Large-collections of pictures from an Internet photo-sharing site, unrelated to the source of those pictures used in the training process have been tested. The experimental results show that a single computer processor can suggest annotation terms in real-time and with good accuracy.  The ALIPR system reduces the time it takes for the users to tag the pictures.  In this talk, I will also provide an overview of our ongoing image database retrieval projects, including SIMPLIcity image similarity search engine, the Story Picturing Engine, image-based security, computational aesthetics, and art and cultural imaging.  Real-life demonstrations of some of the systems will be provided.  This is a joint work with Jia Li of the Department of Statistics at Penn State.

Biography: