Name
Abstract | ||
|---|---|---|
This paper proposes the Bag of Visual Graphs (BoVG), a new approach to encode the spatial relationships of visual words through a codebook of visual-word arrangements, represented by graphs. This graph-based codebook defines a descriptor for image representations that not only considers the frequency of occurrence of visual words, but also their spatial relationships. Experiments demonstrate that BoVG yields high-accuracy scores in classification tasks on the traditional Caltech-101 and Caltech-256 datasets. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/ICIP.2013.6738888 | 2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013) |
Keywords | Field | DocType |
image classification, bag of visual words, spatial relationships, graphs | Graph theory,Computer vision,ENCODE,Graph,Pattern recognition,Bag-of-words model in computer vision,Computer science,Image representation,Artificial intelligence,Contextual image classification,Codebook,Visual Word | Conference |
ISSN | Citations | PageRank |
1522-4880 | 6 | 0.43 |
References | Authors | |
12 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Fernanda B. Silva | 1 | 53 | 2.35 |
| Siome Goldenstein | 2 | 618 | 47.43 |
| Salvatore Tabbone | 3 | 653 | 52.52 |
| Ricardo da Silva Torres | 4 | 787 | 61.46 |