AIC Seminar Series

The need for efficient content-based image retrieval has increased tremendously in many application areas such as biomedicine, military, commerce, education, personal photo management, and Web image classification and searching. In this talk, we present our research in the area of intelligent image indexing and retrieval. We developed a wavelet-based approach for feature extraction and an integrated region matching (IRM) technique for matching region features. An image in the database is represented by a set of regions, roughly corresponding to objects, which are characterized by color, texture, shape, and location. A measure for the overall similarity between images is developed as a region-matching scheme that integrates properties of all the regions in the images. Our recent research focuses on developing ALIP (Automatic Linguistic Indexing of Pictures), a system to index images using automatically learned statistical models. Categorized images are used to train a dictionary of hundreds of concepts automatically based on statistical modeling. Images of any given concept category are regarded as instances of a stochastic process that characterizes the category. To measure the extent of association between an image and the textual description of a category of images, the likelihood of the occurrence of the image based on the stochastic process derived from the category is computed. A high likelihood indicates a strong association. Experiments show that the system has high potential in linguistic indexing of images. In the talk, we will also cover some of our most recent work. Joint work with Jia Li.

James Z. Wang, holder of the endowed PNC Technologies Career Development Professorship, is an assistant professor of the School of Information Sciences and Technology and by courtesy appointments in the Department of Computer Science and Engineering and the Graduate Option on Bioinformatics and Genomics at The Pennsylvania State University. He received a Summa Cum Laude Bachelor’s degree in Mathematics and Computer Science from University of Minnesota (1994), an M.S. in Mathematics and an M.S. in Computer Science, both from Stanford University (1997), and a Ph.D. degree in Medical Information Sciences from Stanford University’s Biomedical Informatics and Database groups (2000). He is a recipient of an NSF Career award in support of his research program. He has authored or co-authored two monographs and more than 50 journal articles, book chapters, and refereed conference papers.

Please arrive at least 10 minutes early in order to sign in and be escorted to the conference room. SRI is located at 333 Ravenswood Avenue in Menlo Park. Visitors may park in the visitors lot in front of Building E, and should follow the instructions by the lobby phone to be escorted to the meeting room. Detailed directions to SRI, as well as maps, are available from the Visiting AIC web page.

©2013 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy