Automatic feedback for content based image retrieval on the Web

Y.A. Aslandogan1, C.T. Yu1
1Department of Computer Science and Engineering, University of Texas, Arlington, USA

Tóm tắt

We address the problem of identifying images of persons in large collections, such as the Web, without an existing face image database. We describe a method and a system that automatically constructs an initial face image database for a person using textual evidence obtained from the Web, and then uses this database for identifying images of that person. The initial retrieval results are obtained via text/HTML analysis and face detection. An internal clustering process groups visually similar faces among these initial results and builds a facial database. This database is then used by a face recognizer. The outputs of the textual and visual evidence modules are combined using Dempster-Shafer (1976) evidence combination formula. We present the results of an experimental evaluation where the system was able to improve upon the detection-only method when text/HTML analysis performed poorly.

Từ khóa

#Feedback #Image retrieval #Content based retrieval #Image databases #Face detection #Visual databases #HTML #Face recognition #Performance analysis #Performance evaluation

Tài liệu tham khảo

mu, 2001, Training algorithms for robust face recognition using a tempiate-matching approach, Proceedings of the 1JCNN'01 gose, 1996, Pattern Recognition and Image Analysis shafer, 1976, A Mathematical Theory of Evidence, 10.1515/9780691214696 cox, 1996, Pichunter Bayesian Relevance Feedback for Image Retrieval, 3, 361 alp aslandogan, 2000, Evaluating strategies and systems for indexing person images on the web, Proceedings of ACM Multimedia 2000, 56 10.1109/69.929893 grosky, 2001, Negotiating the semantic gap: From feature maps to semantic landscapes, Conference on Current Trends in Theory and Practice of Informatics, 33 10.1145/190627.190638 rui, 1998, Relevance feedback techniques in interactive content-based image retrieval, Storage and Retrieval for Image and Video Databases (SPIE), 25 10.1007/BF00962238 10.1145/345508.345553 moghaddam, 1994, Face recognition using view-based and modular eigenspaces, Automatic Systems for the Identification and Inspection of Humans SPIE, 2277, 10.1117/12.191877 dorai, 2001, Bridging the semantic gap in content management systems: Computational media aesthetics, Proceedings of COSIGN 2001 Computational Semiotics for Games and New Media, 33 10.1145/243199.243261 taycher, 1997, Image digestion and relevance feedback in the im-agerover www search engine, Proceedings of SPIE Visual 97