Local Multi-Coordinate System for Object Retrieval

Go IRIE  Yukito WATANABE  Takayuki KUROZUMI  Tetsuya KINEBUCHI  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E99-D   No.10   pp.2656-2660
Publication Date: 2016/10/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2016EDL8109
Type of Manuscript: LETTER
Category: Image Processing and Video Processing
Keyword: 
image retrieval,  local coordinate system,  VLAD,  

Full Text: PDF(149KB)>>
Buy this Article




Summary: 
Encoding multiple SIFT descriptors into a single vector is a key technique for efficient object image retrieval. In this paper, we propose an extension of local coordinate system (LCS) for image representation. The previous LCS approaches encode each SIFT descriptor by a single local coordinate, which is not adequate for localizing its position in the descriptor space. Instead, we use multiple local coordinates to represent each descriptor with PCA-based decorrelation. Experiments show that this simple modification can improve retrieval performance significantly.