@inproceedings{c419af395dbc49599fa2b826da481702,
title = "Probabilistic web image gathering",
abstract = "We propose a new method for automated large scale gath-ering of Web images relevant to specified concepts. Our main goal is to build a knowledge base associated with as many concepts as possible for large scale object recognition studies. A second goal is supporting the building of more accurate text-based indexes for Web images. In our method, good quality candidate sets of images for each keyword are gathered as a function of analysis of the surrounding HTML text. The gathered images are then segmented into regions, and a model for the probability distribution of regions for the concept is computed using an iterative algorithm based on the previous work on statistical image annotation. The learned model is then applied to identify which images are visually relevant to the concept implied by the keyword. Implicitly, which regions or the images are relevant is also determined. Our experiments reveal that the new method performs much better than Google Image Search and a sim-ple method based on more standard content based image retrieval methods.",
keywords = "Image selection, Prob-abilistic method, Web image mining, Web image search",
author = "Keiji Yanai and Kobus Barnard",
note = "Publisher Copyright: Copyright {\textcopyright} 2005 ACM.; 7th ACM SIGMM International Workshop on Multimedia Information Retrieval, MIR 2005 ; Conference date: 10-11-2005 Through 11-11-2005",
year = "2005",
month = nov,
day = "10",
doi = "10.1145/1101826.1101838",
language = "English (US)",
series = "MIR 2005 - Proceedings of the 7th ACM SIGMM International Workshop on Multimedia Information Retrieval, Co-located with ACM Multimedia 2005",
publisher = "Association for Computing Machinery, Inc",
pages = "57--64",
booktitle = "MIR 2005 - Proceedings of the 7th ACM SIGMM International Workshop on Multimedia Information Retrieval, Co-located with ACM Multimedia 2005",
}