Automatic Rating and Selection of Digital Photographs

Authors:
Daniel Kormann;Peter Dunker;Ronny Paduschek
Affiliations:
Fraunhofer Institute for Digital Media Technology, Ilmenau, Germany 98693;Fraunhofer Institute for Digital Media Technology, Ilmenau, Germany 98693;Fraunhofer Institute for Digital Media Technology, Ilmenau, Germany 98693
Venue:
SAMT '09 Proceedings of the 4th International Conference on Semantic and Digital Media Technologies: Semantic Multimedia
Year:
2009

Citing 5
Cited 2

Time as essence for photo browsing through personal digital libraries

Proceedings of the 2nd ACM/IEEE-CS joint conference on Digital libraries
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
MetaXa—Context- and content-driven metadata enhancement for personal photo books

MMM'07 Proceedings of the 13th international conference on Multimedia Modeling - Volume Part I
Studying aesthetics in photographic images using a computational approach

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
Automated event clustering and quality screening of consumer pictures for digital albuming

IEEE Transactions on Multimedia

Photo summary: automated selection of representative photos from a digital collection

Proceedings of the 1st ACM International Conference on Multimedia Retrieval
User experience study of multiple photo streams visualization

BCS-HCI '12 Proceedings of the 26th Annual BCS Interaction Specialist Group Conference on People and Computers

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents methods for automatically rating and selecting digital photographs. The importance of each photograph is estimated by analyzing its content as well as its time-metadata. The presence of people is estimated by combining face and skin detection. Finally, the appeal of each photograph is calculated using a trained SVM classifier. The results of a conducted user study show that the automatically obtained rating coincides well with the perception of the test persons.