|
BOBC |
 |
 |
 |
|
Le, Thanh Nam, et al.. "Subgraph spotting in graph representations of comic book images." Pattern Recognition Letters 112.(2018): 118–24. Added by: joachim (4/5/23, 2:55 PM) Last edited by: joachim (4/5/23, 2:57 PM) |
| Resource type: Journal Article Language: en: English Peer reviewed DOI: 10.1016/j.patrec.2018.06.017 BibTeX citation key: Le2018 Email resource to friend View all bibliographic details  |
Categories: General Keywords: Digitalization Creators: Adam, Burie, Dutta, Foggia, Guérin, Héroux, Le, Lladós, Luqman, Ogier, Rigaud Publisher: Collection: Pattern Recognition Letters |
Views: 40/425
|
| Attachments |
| Abstract |
|
Graph-based representations are the most powerful data structures for extracting, representing and preserving the structural information of underlying data. Subgraph spotting is an interesting research problem, especially for studying and investigating the structural information based content-based image retrieval (CBIR) and query by example (QBE) in image databases. In this paper we address the problem of lack of freely available ground-truthed datasets for subgraph spotting and present a new dataset for subgraph spotting in graph representations of comic book images (SSGCI) with its ground-truth and evaluation protocol. Experimental results of two state-of-the-art methods of subgraph spotting are presented on the new SSGCI dataset.
|
PHP execution time: 0.05610 s
SQL execution time: 0.09147 s
TPL rendering time: 0.00276 s
Total elapsed time: 0.15033 s
Peak memory usage: 5.2934 MB
Memory at close: 1.2039 MB
Database queries: 76