Image retrieval with multi-stage filtering in low dimensions

K. Inoue, K. Urahama

Research output: Contribution to journalArticlepeer-review


A method is presented for kNN search of images with the aid of two-stage altering which is an extension of an improved single-stage altering method presented by Seidl et al. The two-stage altering method is applied to image retrieval. Three kinds of feature vectors are examined for color-based representation of image contents, those are color histograms, block-partitioned histograms and pixel color vectors. It is veriaed that retrieval time is shortened by extension of altering to two-stage for all of these feature vectors.

Original languageEnglish
Article number1237686
Pages (from-to)182-185
Number of pages4
JournalProceedings - IEEE International Conference on Multimedia and Expo
Publication statusPublished - 2001

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications


Dive into the research topics of 'Image retrieval with multi-stage filtering in low dimensions'. Together they form a unique fingerprint.

Cite this