Conference paper Open Access

Image Aesthetics Assessment using Fully Convolutional Neural Networks

Apostolidis, Konstantinos; Mezaris, Vasileios

This paper presents a new method for assessing the aesthetic quality of images. Based on the findings of previous works on this topic, we propose a method that addresses the shortcomings of existing ones, by: a) Making possible to feed higher-resolution images in the network, by introducing a fully convolutional neural network as the classier. b) Maintaining the original aspect ratio of images in the input of the network, to avoid distortions caused by re-scaling. And c) combining local and global features from the image for making the assessment of its aesthetic quality. The proposed method is shown to achieve state of the art results on a standard large-scale benchmark dataset.

Files (1.0 MB)
Name Size
mmm19_lncs11295_1_preprint.pdf
md5:643f704a349dad189342a67807bd3c22
1.0 MB Download
51
36
views
downloads
Views 51
Downloads 36
Data volume 36.8 MB
Unique views 50
Unique downloads 32

Share

Cite as