2013 Fiscal Year Final Research Report

Development of Image Retrieval System by Considering People Co-occurrence Relations through Relevance Feedback

Research Project

Project/Area Number	23700117
Research Category	Grant-in-Aid for Young Scientists (B)
Allocation Type	Multi-year Fund
Research Field	Media informatics/Database
Research Institution	Osaka University
Principal Investigator	NITTA Naoko 大阪大学, 工学(系)研究科(研究院), 講師 (00379132)
Project Period (FY)	2011 – 2012
Keywords	人物画像検索 / 適合性フィードバック / 共起関係 / クラス分類 / 能動学習 / 構造化
Research Abstract	Group photos often contain socially related people such as family and friends. We developed a system for retrieving images containing a specific target person from a group photo collection by considering people co-occurrence relations. A Bag of People (BoP) feature, which represents both the facial appearances of persons and their co-occurrence relations, is extracted from each image. By using the BoP features, a classifier for classifying images into two classes, images containing the target person and other images, can be trained. The images determined to contain the target person by the classifier are presented to the user as the retrieval results. The classifier is re-trained by a small number of correctly retrieved images which are selected by the user. When retrieving images of 32 persons from 1791 group photos, the mean average precision improved from 20% to 70% after five feedback iterations.

(5 results)