|
BOBC |
 |
 |
 |
|
Nguyen, Nhu-Van, Christophe Rigaud und Jean-Christophe Burie: "Digital Comics Image Indexing Based on Deep Learning." In: Journal of Imaging 4.7 (2018)<https://www.mdpi.com/2313-433X/4/7/89>. Added by: joachim (2020-06-28 14:19) Last edited by: joachim (2021-06-24 12:30) |
| Resource type: Web Article Languages: English Peer reviewed DOI: 10.3390/jimaging4070089 BibTeX citation key: Nguyen2018a Email resource to friend View all bibliographic details  |
Categories: General Keywords: Comics research, Digitalization Creators: Burie, Nguyen, Rigaud Collection: Journal of Imaging |
Views: 3/83
|
| Attachments | URLs https://www.mdpi.com/2313-433X/4/7/89 |
| Abstract |
|
The digital comic book market is growing every year now, mixing digitized and digital-born comics. Digitized comics suffer from a limited automatic content understanding which restricts online content search and reading applications. This study shows how to combine state-of-the-art image analysis methods to encode and index images into an XML-like text file. Content description file can then be used to automatically split comic book images into sub-images corresponding to panels easily indexable with relevant information about their respective content. This allows advanced search in keywords said by specific comic characters, action and scene retrieval using natural language processing. We get down to panel, balloon, text, comic character and face detection using traditional approaches and breakthrough deep learning models, and also text recognition using LSTM model. Evaluations on a dataset composed of online library content are presented, and a new public dataset is also proposed.
|
PHP execution time: 0.04994 s
SQL execution time: 0.09274 s
TPL rendering time: 0.00227 s
Total elapsed time: 0.14495 s
Peak memory usage: 1.3017 MB
Memory at close: 1.2507 MB
Database queries: 65