Artistic movement recognition by boosted fusion of color structure and topographic description
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
Artistic movement recognition by boosted fusion of color structure and topographic description. / Florea, Corneliu; Toca, Cosmin; Gieseke, Fabian Cristian.
Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision. IEEE, 2017. s. 569-577.Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Artistic movement recognition by boosted fusion of color structure and topographic description
AU - Florea, Corneliu
AU - Toca, Cosmin
AU - Gieseke, Fabian Cristian
N1 - Conference code: 17
PY - 2017/5/11
Y1 - 2017/5/11
N2 - We address the problem of automatically recognizing artistic movement in digitized paintings. We make the following contributions: Firstly, we introduce a large digitized painting database that contains refined annotations of artistic movement. Secondly, we propose a new system for the automatic categorization that resorts to image descriptions by color structure and novel topographical features as well as to an adapted boosted ensemble of support vector machines. The system manages to isolate initially misclassified images and to correct such errors in further stages of the boosting process. The resulting performance of the system compares favorably with classical solutions in terms of accuracy and even manages to outperform modern deep learning frameworks.
AB - We address the problem of automatically recognizing artistic movement in digitized paintings. We make the following contributions: Firstly, we introduce a large digitized painting database that contains refined annotations of artistic movement. Secondly, we propose a new system for the automatic categorization that resorts to image descriptions by color structure and novel topographical features as well as to an adapted boosted ensemble of support vector machines. The system manages to isolate initially misclassified images and to correct such errors in further stages of the boosting process. The resulting performance of the system compares favorably with classical solutions in terms of accuracy and even manages to outperform modern deep learning frameworks.
UR - http://www.scopus.com/inward/record.url?scp=85020228047&partnerID=8YFLogxK
U2 - 10.1109/WACV.2017.69
DO - 10.1109/WACV.2017.69
M3 - Article in proceedings
AN - SCOPUS:85020228047
SP - 569
EP - 577
BT - Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision
PB - IEEE
Y2 - 24 March 2017 through 31 March 2017
ER -
ID: 179556482