Evaluating Strategies and Systems for COntnet Based Indexing of Person Images on the Web

摘要

Content based indexing of multimedia has alwasy been a challenging task. THe enormity and the diversity of the multimedia content on the web adds another dimension to this challenge. In this paper, we examine ways of combining visual and textual information for contetn based indexing of multimedia on the web. In particular, wer examine different metods of combining evidences due to face detection, Text/HTML analysis and face recogntiion for identifying person images. We provide experiemntal evaluation of the following strategies: i) Face detection on the image followed by Text/HTML nalaysis of the containing apge; ii) face detection followed by face recognition; iii) face detection followed by a linear combination of evidences due to text/HTML anlaysis and face recognition; and iv) face detection followed by a Dempster-Shafer combination of evidences due to text/HTML analysis and face recognition.