• 研究課題をさがす
  • 研究者をさがす
  • KAKENの使い方
  1. 課題ページに戻る

2014 年度 実績報告書

ラベル伝播による画像データセットにおける顔への自動ラベル付け手法

研究課題

研究課題/領域番号 24500135
研究機関国立情報学研究所

研究代表者

MICHAEL E.Houle  国立情報学研究所, 大学共同利用機関等の部局等, 客員教授 (90399270)

研究分担者 佐藤 真一  国立情報学研究所, コンテンツ科学研究系, 教授 (90249938)
研究期間 (年度) 2012-04-01 – 2015-03-31
キーワードclassification / label propagation / similarity graph / face images / multimedia / sparsification
研究実績の概要

Although much research effort has been put into face recognition, the problem remains very difficult. The aim of this project is to use the redundancy in the database to expand the annotation of face images, by building a reasoning system with the aim of propagating as much as possible the face labels.

The outcomes of the first year of the project led us to believe that the performance of our label propagation methods depended crucially on the quality of the similarity graph used. Accordingly, in the final year of the project, we focused on what turned out to be the central issue: the dynamic modification of the similarity graph in order to enhance the quality of image labeling produced by the propagation process. The main outcome was a very successful graph construction method based on the following strategy. For each instance of a tagged image, the relevance of each of its features is assessed according to the discriminability of the similarity measure over all other tagged images, with respect to the single feature. Then, the tagged image is associated with a reduced set of its own most discriminative features. These features are then used to customize the similarity values between tagged and untagged faces in the graph construction.

These methods required the efficient on-demand computation of similarity values using subsets of the original feature set. To support such computation, we investigated fast approximate similarity search using precomputed approximations to a target similarity measure supplied at query time.

備考

Our conference paper "Efficient Algorithms for Similarity Search in Axis-Aligned Subspaces" won the SISAP 2014 Best Paper Award.

  • 研究成果

    (3件)

すべて 2014

すべて 雑誌論文 (1件) (うち査読あり 1件、 謝辞記載あり 1件) 学会発表 (2件)

  • [雑誌論文] Improving the Quality of K-NN Graphs through Vector Sparsification: Application to Image Databases2014

    • 著者名/発表者名
      M, E. Houle, X. Ma, V. Oria, and J. Sun
    • 雑誌名

      International Journal of Multimedia Information Retrieval

      巻: 3(4) ページ: 259-274

    • DOI

      10.1007/s13735-014-0067-7

    • 査読あり / 謝辞記載あり
  • [学会発表] Efficient Algorithms for Similarity Search in Axis-Aligned Subspaces2014

    • 著者名/発表者名
      M, E. Houle, X. Ma, V. Oria, and J. Sun
    • 学会等名
      7th International Conference on Similarity Search and Applications (SISAP 2014)
    • 発表場所
      Los Cabos, Mexico
    • 年月日
      2014-10-29 – 2014-10-31
  • [学会発表] Improving the Quality of K-NN Graphs for Image Databases through Vector Sparsification2014

    • 著者名/発表者名
      M, E. Houle, X. Ma, V. Oria, and J. Sun
    • 学会等名
      5th ACM International Conference on Multimedia Retrieval (ICMR 2014)
    • 発表場所
      Glasgow, UK
    • 年月日
      2014-04-01 – 2014-04-04

URL: 

公開日: 2016-06-01  

サービス概要 検索マニュアル よくある質問 お知らせ 利用規程 科研費による研究の帰属

Powered by NII kakenhi