Presentation 2008-12-19
Annotation method of segmented regions using a number of feature points shared among different images
Yuichi YOSHIDA, Mitsuru AMBAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose an object annotation method for images obtained by widely available search engines on internet. The goal of this research is to extract the common objects from a large number of images and label them by the query words. Our method analyzes images retrieved from search engines and performs segmentation based on shared local visual features. Images retrieved from search engines presumably contain the same objects that represent the query words. Then the extracted common regions are labeled by the query words. Such object recognition method would open the doors to new applications in web services. For instance, it can make images be "clickable". We performed an experiment by using images retrieved from "Google Image Search". We present the concept of proposed method and results of the experiment.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) annotation / segmentation / local feature description / image search
Paper # PRMU2008-176
Date of Issue

Conference Information
Committee PRMU
Conference Date 2008/12/11(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) Annotation method of segmented regions using a number of feature points shared among different images
Sub Title (in English)
Keyword(1) annotation
Keyword(2) segmentation
Keyword(3) local feature description
Keyword(4) image search
1st Author's Name Yuichi YOSHIDA
1st Author's Affiliation DENSO IT LABORATORY, INC.()
2nd Author's Name Mitsuru AMBAI
2nd Author's Affiliation DENSO IT LABORATORY, INC.
Date 2008-12-19
Paper # PRMU2008-176
Volume (vol) vol.108
Number (no) 363
Page pp.pp.-
#Pages 6
Date of Issue