Abstract

Computational visual aesthetics has recently become an active research area. Existing state-of-art methods formulate this as a binary classification task where a given image is predicted to be beautiful or not. In many applications such as image retrieval and enhancement, it is more important to rank images based on their aesthetic quality instead of binary-categorizing them. Furthermore, in such applications, it may be possible that all images belong to the same category. Hence determining the aesthetic ranking of the images is more appropriate. To this end, we formulate a novel problem of ranking images with respect to their aesthetic quality. We construct a new dataset of image pairs with relative labels by carefully selecting images from the popular AVA dataset. Unlike in aesthetics classification, there is no single threshold which would determine the ranking order of the images across our entire dataset. We propose a deep neural network based approach that is trained on image pairs by incorporating principles from relative learning. Results show that such relative training procedure allows our network to rank the images with a higher accuracy than a state-of-art network trained on the same set of images using binary labels.

Original languageEnglish (US)
Title of host publication2016 23rd International Conference on Pattern Recognition, ICPR 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2446-2451
Number of pages6
ISBN (Electronic)9781509048472
DOIs
StatePublished - Apr 13 2017
Event23rd International Conference on Pattern Recognition, ICPR 2016 - Cancun, Mexico
Duration: Dec 4 2016Dec 8 2016

Other

Other23rd International Conference on Pattern Recognition, ICPR 2016
CountryMexico
CityCancun
Period12/4/1612/8/16

Fingerprint

Labels
Binary images
Image enhancement
Image retrieval
Deep neural networks

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Gattupalli, V., Chandakkar, P. S., & Li, B. (2017). A computational approach to relative aesthetics. In 2016 23rd International Conference on Pattern Recognition, ICPR 2016 (pp. 2446-2451). [7900003] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2016.7900003

A computational approach to relative aesthetics. / Gattupalli, Vijetha; Chandakkar, Parag S.; Li, Baoxin.

2016 23rd International Conference on Pattern Recognition, ICPR 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 2446-2451 7900003.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gattupalli, V, Chandakkar, PS & Li, B 2017, A computational approach to relative aesthetics. in 2016 23rd International Conference on Pattern Recognition, ICPR 2016., 7900003, Institute of Electrical and Electronics Engineers Inc., pp. 2446-2451, 23rd International Conference on Pattern Recognition, ICPR 2016, Cancun, Mexico, 12/4/16. https://doi.org/10.1109/ICPR.2016.7900003
Gattupalli V, Chandakkar PS, Li B. A computational approach to relative aesthetics. In 2016 23rd International Conference on Pattern Recognition, ICPR 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 2446-2451. 7900003 https://doi.org/10.1109/ICPR.2016.7900003
Gattupalli, Vijetha ; Chandakkar, Parag S. ; Li, Baoxin. / A computational approach to relative aesthetics. 2016 23rd International Conference on Pattern Recognition, ICPR 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 2446-2451
@inproceedings{f86897eca5374d82ac34e8e7ae557181,
title = "A computational approach to relative aesthetics",
abstract = "Computational visual aesthetics has recently become an active research area. Existing state-of-art methods formulate this as a binary classification task where a given image is predicted to be beautiful or not. In many applications such as image retrieval and enhancement, it is more important to rank images based on their aesthetic quality instead of binary-categorizing them. Furthermore, in such applications, it may be possible that all images belong to the same category. Hence determining the aesthetic ranking of the images is more appropriate. To this end, we formulate a novel problem of ranking images with respect to their aesthetic quality. We construct a new dataset of image pairs with relative labels by carefully selecting images from the popular AVA dataset. Unlike in aesthetics classification, there is no single threshold which would determine the ranking order of the images across our entire dataset. We propose a deep neural network based approach that is trained on image pairs by incorporating principles from relative learning. Results show that such relative training procedure allows our network to rank the images with a higher accuracy than a state-of-art network trained on the same set of images using binary labels.",
author = "Vijetha Gattupalli and Chandakkar, {Parag S.} and Baoxin Li",
year = "2017",
month = "4",
day = "13",
doi = "10.1109/ICPR.2016.7900003",
language = "English (US)",
pages = "2446--2451",
booktitle = "2016 23rd International Conference on Pattern Recognition, ICPR 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - A computational approach to relative aesthetics

AU - Gattupalli, Vijetha

AU - Chandakkar, Parag S.

AU - Li, Baoxin

PY - 2017/4/13

Y1 - 2017/4/13

N2 - Computational visual aesthetics has recently become an active research area. Existing state-of-art methods formulate this as a binary classification task where a given image is predicted to be beautiful or not. In many applications such as image retrieval and enhancement, it is more important to rank images based on their aesthetic quality instead of binary-categorizing them. Furthermore, in such applications, it may be possible that all images belong to the same category. Hence determining the aesthetic ranking of the images is more appropriate. To this end, we formulate a novel problem of ranking images with respect to their aesthetic quality. We construct a new dataset of image pairs with relative labels by carefully selecting images from the popular AVA dataset. Unlike in aesthetics classification, there is no single threshold which would determine the ranking order of the images across our entire dataset. We propose a deep neural network based approach that is trained on image pairs by incorporating principles from relative learning. Results show that such relative training procedure allows our network to rank the images with a higher accuracy than a state-of-art network trained on the same set of images using binary labels.

AB - Computational visual aesthetics has recently become an active research area. Existing state-of-art methods formulate this as a binary classification task where a given image is predicted to be beautiful or not. In many applications such as image retrieval and enhancement, it is more important to rank images based on their aesthetic quality instead of binary-categorizing them. Furthermore, in such applications, it may be possible that all images belong to the same category. Hence determining the aesthetic ranking of the images is more appropriate. To this end, we formulate a novel problem of ranking images with respect to their aesthetic quality. We construct a new dataset of image pairs with relative labels by carefully selecting images from the popular AVA dataset. Unlike in aesthetics classification, there is no single threshold which would determine the ranking order of the images across our entire dataset. We propose a deep neural network based approach that is trained on image pairs by incorporating principles from relative learning. Results show that such relative training procedure allows our network to rank the images with a higher accuracy than a state-of-art network trained on the same set of images using binary labels.

UR - http://www.scopus.com/inward/record.url?scp=85019075661&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019075661&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2016.7900003

DO - 10.1109/ICPR.2016.7900003

M3 - Conference contribution

SP - 2446

EP - 2451

BT - 2016 23rd International Conference on Pattern Recognition, ICPR 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -