Mahalanobis encodings for visual categorization

Tomoki Matsuzawa, Raissa Relator, Wataru Takei, Shinichiro Omachi, Tsuyoshi Kato

研究成果: Article査読

1 被引用数 (Scopus)

抄録

Nowadays, the design of the representation of images is one of the most crucial factors in the performance of visual categorization. A common pipeline employed in most of recent researches for obtaining an image representation consists of two steps: the encoding step and the pooling step. In this paper, we introduce the Mahalanobis metric to the two popular image patch encoding modules, Histogram Encoding and Fisher Encoding, that are used for Bag-of-Visual-Word method and Fisher Vector method, respectively. Moreover, for the proposed Fisher Vector method, a close-form approximation of Fisher Vector can be derived with the same assumption used in the original Fisher Vector, and the codebook is built without resorting to time-consuming EM (Expectation-Maximization) steps. Experimental evaluation of multi-class classification demonstrates the effectiveness of the proposed encoding methods.

本文言語English
ページ(範囲)69-73
ページ数5
ジャーナルIPSJ Transactions on Computer Vision and Applications
7
DOI
出版ステータスPublished - 2015

ASJC Scopus subject areas

  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Mahalanobis encodings for visual categorization」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル