Abstract | ||
---|---|---|
We present a new approach to the problem of grouping similar scene images. The proposed method characterizes both the global feature layout and the local oriented edge responses of an image, and provides a translation-invariant similarity measure to compare scene images. Our method is effective in generating initial clustering results for applications that require extensive local-feature matching on unorganized image collections, such as large-scale 3D reconstruction and scene completion. The advantage of our method is that it can estimate image similarity via integrating global and local information. The experimental evaluations on various image datasets show that our method is able to approximate well the similarities derived from local-feature matching with a lower computational cost. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ACPR.2011.6166542 | ACPR |
Keywords | DocType | ISBN |
pattern clustering,image matching,large-scale 3d reconstruction,gist descriptor,global feature layout,image reconstruction,scene clustering,translation-invariant scene grouping,unorganized image collections,phase-only correlation,extensive local-feature matching,similar scene images grouping,local oriented edge responses,scene completion,sift descriptor,3d reconstruction,correlation,layout,internet,three dimensional,computational modeling,computer model,indium tin oxide | Conference | 978-1-4577-0122-1 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pin-Ching Su | 1 | 0 | 0.34 |
Hwann-Tzong Chen | 2 | 826 | 52.13 |
Koichi Ito | 3 | 18 | 5.48 |
Takafumi Aoki | 4 | 915 | 125.99 |