Presentation 1999/3/19
Landmark Recognition with Eigen-Window
Sanae MURAKAMI, Susumu HORIGUCHI, Toru ABE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) To estimate current location from an input image, a method for recognizing landmarks in the image with the eigen-window technique is described. In the eigen-window technique, small windows called eigen-window are set in an input image, and these windows are compared with the eigen-window in the training images. In this article, we propose a method to select the eigen-window regions that are suitable for object recognition and parameter estimation from an input image. Furthermore, we propose a novel method for hierarchical-clustering of eigen-window, and to improve searching efficiency of the eigen-window technique, we apply the proposed method to construct the tree-structured dictionaries.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) landmark recognition / visual learning / eigen-window / hierarchical-clustering / discriminant analysis.
Paper # PRMU98-257
Date of Issue

Conference Information
Committee PRMU
Conference Date 1999/3/19(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Landmark Recognition with Eigen-Window
Sub Title (in English)
Keyword(1) landmark recognition
Keyword(2) visual learning
Keyword(3) eigen-window
Keyword(4) hierarchical-clustering
Keyword(5) discriminant analysis.
1st Author's Name Sanae MURAKAMI
1st Author's Affiliation School of Information Science, Japan Advanced Institute of Science and Technology()
2nd Author's Name Susumu HORIGUCHI
2nd Author's Affiliation School of Information Science, Japan Advanced Institute of Science and Technology
3rd Author's Name Toru ABE
3rd Author's Affiliation School of Information Science, Japan Advanced Institute of Science and Technology
Date 1999/3/19
Paper # PRMU98-257
Volume (vol) vol.98
Number (no) 678
Page pp.pp.-
#Pages 8
Date of Issue