Color descriptor for content-based drawing retrieval

被引：11

作者：

Rigaud, Christophe ^{[1
]}

Burie, Jean-Christophe ^{[1
]}

Ogier, Jean-Marc ^{[1
]}

Karatzas, Dimosthenis ^{[2
]}

机构：

[1] Univ La Rochelle, Lab L3i, F-17042 La Rochelle, France

[2] Univ Autonoma Barcelona, Comp Vis Ctr, E-08193 Bellaterra, Barcelona, Spain

来源：

2014 11TH IAPR INTERNATIONAL WORKSHOP ON DOCUMENT ANALYSIS SYSTEMS (DAS 2014) | 2014年

关键词：

color descriptor; non-rigid object; drawing retrieval; color palette; comics analysis; TIME;

D O I：

10.1109/DAS.2014.70

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Human detection in computer vision field is an active field of research. Extending this to human-like drawings such as the main characters in comic book stories is not trivial. Comics analysis is a very recent field of research at the intersection of graphics, texts, objects and people recognition. The detection of the main comic characters is an essential step towards a fully automatic comic book understanding. This paper presents a color-based approach for comics character retrieval using content-based drawing retrieval and color palette.

引用

页码：267 / 271

页数：5

共 17 条

[1]

AHMAD H. A., 2012, B JSSD, V59

[2]

[Anonymous], P 10 IAPR INT WORKSH

[3]

[Anonymous], 2005, PROC CVPR IEEE

[4]

[Anonymous], 2010, THESIS INSA DE LYON

[5]

Chowdhury GG., 2010, Introduction to Modern Information Retrieval

[6] The limits of time and transitions: challenges to theories of sequential image comprehension [J].

Cohn, Neil .

STUDIES IN COMICS, 2010, 1 (01) :127-147

[7]

Guerin C., 2013, P INT C DOC AN REC I

[8]

Khan F. S., 2012, 25 IEEE C COMP VIS P

[9] Discerning pictures: how we look at and understand images in comics [J].

Medley, Stuart .

STUDIES IN COMICS, 2010, 1 (01) :53-70

[10]

RIGAUD C, 2013, P 8 INT C COMP VIS T

← 1 2 →