Paper Info
Title
The Good, the Bad, and the Ugly: Predicting Aesthetic Image Labels
Abstract
Automatic classification of the aesthetic content of a picture is one of the challenges in the emerging discipline of computational aesthetics. Any suitable solution must cope with the facts that aesthetic experiences are highly subjective and that a commonly agreed upon theory of their psychological constituents is still missing. In this paper, we present results obtained from an empirical basis of several thousand images. We train SVM based classifiers to predict aesthetic adjectives rather than aesthetic scores and we introduce a probabilistic post processing step that alleviates effects due to misleadingly labeled training data. Extensive experimentation indicates that aesthetics classification is possible to a large extent. In particular, we find that previously established low-level features are well suited to recognize beauty. Robust recognition of unseemliness, on the other hand, appears to require more high-level analysis.
Year
DOI
Venue
2010
10.1109/ICPR.2010.392
ICPR
Keywords
Field
DocType
probabilistic post processing,automatic classification,aesthetics classification,extensive experimentation,svm,aesthetic experience,computational aesthetics,image classification,alleviates effect,predicting aesthetic image labels,aesthetic image label prediction,aesthetic adjective,psychological constituents,aesthetic score,empirical basis,aesthetic content,support vector machines,probability,visualization,accuracy,psychology,image recognition
Training set,Computer vision,Computer science,Visualization,Support vector machine,Beauty,Artificial intelligence,Probabilistic logic,Contextual image classification,Computational aesthetics,Machine learning,Form of the Good
Conference
ISSN
ISBN
Citations 
1051-4651
978-1-4244-7542-1
12
PageRank 
References 
Authors
0.64
3
3
Name
Order
Citations
PageRank
Yaowen Wu1120.98
Christian Bauckhage21979195.86
Christian Thurau347834.19