Method for Automatic E-Comic Scene Frame Extraction for Reading Comic on Mobile Devices

Arai, Kohei; Tolle, Herman

doi:10.1109/itng.2010.22

Cited by 25 publications

(24 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods do not consider empty area [15] and border-free panels. These issues have been corrected by connected component labeling approaches, but these approaches are sensitive to regions that sometimes connect several panels, which potentially increases the detection error rate [20,21]. Another approach based on morphological analysis and region growing can remove such connecting elements but at the same time create new holes in the panel border [22].…”

Section: Panelsmentioning

confidence: 99%

Digital Comics Image Indexing Based on Deep Learning

2018

View full text Add to dashboard Cite

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.

show abstract

Section: Panelsmentioning

confidence: 99%

Digital Comics Image Indexing Based on Deep Learning

2018

View full text Add to dashboard Cite

show abstract

“…These methods doesn't handle empty area (case missing) [9] within a strip (figure 1a) or no full border frame (figure 1b). These issues have been corrected by connected-component approaches [1] but if some elements overlap (figure 1c), the frame segmentation process failed. The regions of interest (ROI) are often clustered by heuristic [2,13] relative to the page size that is width and height dependent.…”

Section: Frame Segmentationmentioning

confidence: 99%

“…It is probably the reason why it is the only type of text studied so far. Previous works extract text from speech balloon [18,1] or inversely speech balloon from text [13]. These approaches are really efficient but they suppose that text is written in black in a white balloon.…”

Section: Text Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Robust Frame and Text Extraction from Comic Books

Rigaud

Tsopzé

Burie

et al. 2013

Graphics Recognition. New Trends and Challenges

View full text Add to dashboard Cite

Abstract. Comic books constitute an important heritage in many countries. Nowadays, digitization allows to search directly from content instead of metadata only (e.g. album title or author name). Few studies have been done in this direction. Only frame and speech balloon extraction have been experimented in the case of simple page structure. In fact, the page structure depends on the author which is why many different structures and drawings exist. Despite the differences, drawings have a common characteristic because of design process: they are all surrounded by a black line. In this paper, we propose to rely on this particularity of comic books to automatically extract frame and text using a connectedcomponent labeling analysis. The approach is compared with some existing methods found in the literature and results are presented.

show abstract

“…We also give some description about Manga content creation as the improvement of the previous research work [6] [7].…”

Section: Background On Manga Features and Mobile Comic Content Crmentioning

confidence: 99%

Manga content extraction method for automatic mobile comic content creation

Tolle

Arai

2013

2013 International Conference on Advanced Computer Science and Information Systems (ICACSIS)

Self Cite

View full text Add to dashboard Cite

Creating a digital Manga comic for mobile devices is chalenging because of the limitation of device's screen size and time consuming of the process. In this paper, we proposed an efficient method for automatically creating mobile content of digital Manga comic from scanned of printed digital comic by extracting comic frame, comic balloon and Japanese character within a Manga comic then recompose it a new mobile content using ComicXML to store comic frame content information. Experimental results on Manga content extraction have 81.6% accuracy of non-flat comic page frame extraction, 100% accuracy of comic balloon detection, and about 93.75% accuracy of Japanese character text extraction.

show abstract

Method for Automatic E-Comic Scene Frame Extraction for Reading Comic on Mobile Devices

Cited by 25 publications

References 1 publication

Digital Comics Image Indexing Based on Deep Learning

Digital Comics Image Indexing Based on Deep Learning

Robust Frame and Text Extraction from Comic Books

Manga content extraction method for automatic mobile comic content creation

Contact Info

Product

Resources

About