Title :
Image aesthetics depends on context
Author :
Florian Simond;Nikolaos Arvanitopoulos;Sabine Süsstrunk
Author_Institution :
School of Computer and Communication Sciences, É
Abstract :
We investigate the influence of low-level image features for aesthetics prediction. We show that the aesthetic quality of a photography depends on its context. Image features learned from a specific image category are not necessarily the same as features learned from a generic image collection. Experiments conducted on specific image categories show that specific features obtain statistically significantly better results than generic ones.
Keywords :
"Feature extraction","Image color analysis","Brightness","Animals","Semantics","Context","Reliability"
Conference_Titel :
Image Processing (ICIP), 2015 IEEE International Conference on
DOI :
10.1109/ICIP.2015.7351513