Name
Abstract | ||
|---|---|---|
In this paper, we propose a method to recognize food images which include multiple food items considering co-occurrence statistics of food items. The proposed method employs a manifold ranking method which has been applied to image retrieval successfully in the literature. In the experiments, we prepared co-occurrence matrices of 100 food items using various kinds of data sources including Web texts, Web food blogs and our own food database, and evaluated the final results obtained by applying manifold ranking. As results, it has been proved that co-occurrence statistics obtained from a food photo database is very helpful to improve the classification rate within the top ten candidates. |
Year | Venue | Keywords |
|---|---|---|
2012 | ICPR | Web sites,image classification,image retrieval,matrix algebra,statistical analysis,text analysis,visual databases,Web food blogs,Web texts,cooccurrence matrices,data sources,food database,food item cooccurrence statistics,food photo database,image classification rate improvement,image retrieval,manifold ranking method,multiple-food image recognition |
Field | DocType | ISSN |
Data mining,Computer science,Food recognition,Matrix algebra,Image retrieval,Artificial intelligence,Contextual image classification,Manifold ranking,Information retrieval,Pattern recognition,Co-occurrence,Classification rate,Statistical analysis | Conference | 1051-4651 |
Citations | PageRank | References |
20 | 0.96 | 11 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yuji Matsuda | 1 | 20 | 0.96 |
| Keiji Yanai | 2 | 908 | 98.05 |