Department of Computer Engineering
S E M I N A R
Interesting Faces in News
Effective and efficient retrieval, organization and analysis of large quantities of multi-modal data constitutes a big challenge. News photographs on the web are rich sources of information and accessing them is especially important. News mostly consist of stories about people; therefore, queries related to a specific person are desired. The usual way to retrieve information related to a person is to search using his/her name in the caption. However, such an approach is likely to yield incorrect results. In order to retrieve the correct images of a particular person, visual information must be incorporated and the face of the person needs to be recognized. Hence, we propose a method to retrieve the correct faces of a queried person using both text and visual appearances. On the assumption that a person's face is likely to appear when his/her name is mentioned in the caption, first all the faces associated with the query name are selected. Among these faces, there could be many faces corresponding to the queried person in different conditions, poses and times, but there could also be other faces corresponding to other people in the caption or some non-face images due to the errors in the face detection method used. However, in most cases, the number of corresponding faces of the queried person will be large, and these faces will be more similar to each other than to others. In our study, we propose a graph-based method to find the most similar subset among the set of possible faces associated with the query name, where the most similar subset is likely to correspond to the faces of the queried person.
DATE: December5, 2005, Monday@ 16:40
PLACE: EA 409