Image aesthetic predictors based on weighted CNNs
Authors:
- 19 August 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2291-2295
Abstract
Convolutional Neural Networks (CNNs) have been widely adopted for many imaging applications. For image aesthetics prediction, state-of-the-art algorithms train CNNs on a recently-published large-scale dataset, AVA. However, the distribution of the aesthetic scores on this dataset is extremely unbalanced, which limits the prediction capability of existing methods. We overcome such limitation by using weighted CNNs. We train a regression model that improves the prediction accuracy of the aesthetic scores over state-of-the-art algorithms. In addition, we propose a novel histogram prediction model that not only predicts the aesthetic score, but also estimates the difficulty of performing aesthetics assessment for an input image. We further show an image enhancement application where we obtain an aesthetically pleasing crop of an input image using our regression model.Keywords
This publication has 16 references indexed in Scilit:
- Visual aesthetic quality assessment with a regression model2015
- Image quality evaluation using image quality ruler and graphical model2015
- Going deeper with convolutions2015
- RAPID2014
- AVA: A large-scale database for aesthetic visual analysis2012
- Assessing the aesthetic quality of photographs using generic image descriptors2011
- Content-based photo quality assessment2011
- Fisher Vectors: Beyond Bag-of-Visual-Words Image RepresentationsCommunications in Computer and Information Science, 2011
- Improving the Fisher Kernel for Large-Scale Image Classification2010
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004