TY - GEN
T1 - Aesthetic evaluation of facial portraits using compositional augmentation for deep CNNs
AU - Kairanbay, Magzhan
AU - See, John
AU - Wong, Lai-Kuan
N1 - Publisher Copyright:
© Springer International Publishing AG 2017.
Copyright:
Copyright 2017 Elsevier B.V., All rights reserved.
PY - 2017/3/16
Y1 - 2017/3/16
N2 - Digital facial portrait photographs make up a massive portion of photos in the web. A number of methods for evaluating the aesthetics of photographs have been proposed recently. However, there have been a little work in the research community to address the aesthetics of targeted image domain, such as portraits. This paper introduces a new compositional-based augmentation scheme for aesthetic evaluation of portraits by well-known deep convolutional neural network (DCNN) models. We present a set of feature augmentation methods that take into account compositional photographic rules to ensure that the aesthetic in portraits are not hindered by standard transformations used for DCNN models. On a portrait subset of the large-scale AVA dataset, the proposed approach demonstrated a reasonable improvement in classification performance over the baseline and vanilla deep learning approaches.
AB - Digital facial portrait photographs make up a massive portion of photos in the web. A number of methods for evaluating the aesthetics of photographs have been proposed recently. However, there have been a little work in the research community to address the aesthetics of targeted image domain, such as portraits. This paper introduces a new compositional-based augmentation scheme for aesthetic evaluation of portraits by well-known deep convolutional neural network (DCNN) models. We present a set of feature augmentation methods that take into account compositional photographic rules to ensure that the aesthetic in portraits are not hindered by standard transformations used for DCNN models. On a portrait subset of the large-scale AVA dataset, the proposed approach demonstrated a reasonable improvement in classification performance over the baseline and vanilla deep learning approaches.
UR - http://www.scopus.com/inward/record.url?scp=85016131968&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-54427-4_34
DO - 10.1007/978-3-319-54427-4_34
M3 - Conference contribution
AN - SCOPUS:85016131968
SN - 9783319544267
T3 - Lecture Notes in Computer Science
SP - 462
EP - 474
BT - Computer Vision – ACCV 2016 Workshops. ACCV 2016
A2 - Chen, Chu-Song
A2 - Lu, Jiwen
A2 - Ma, Kai-Kuang
PB - Springer
T2 - 13th Asian Conference on Computer Vision 2016
Y2 - 20 November 2016 through 24 November 2016
ER -