Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICIP.2009.5413825
Title: Saliency-enhanced image aesthetics class prediction
Authors: Wong, L.-K.
Low, K.-L. 
Keywords: Aesthetics
Classification
Saliency
Issue Date: 2009
Citation: Wong, L.-K.,Low, K.-L. (2009). Saliency-enhanced image aesthetics class prediction. Proceedings - International Conference on Image Processing, ICIP : 997-1000. ScholarBank@NUS Repository. https://doi.org/10.1109/ICIP.2009.5413825
Abstract: We present a saliency-enhanced method for the classification of professional photos and snapshots. First, we extract the salient regions from an image by utilizing a visual saliency model. We assume that the salient regions contain the photo subject. Then, in addition to a set of discriminative global image features, we extract a set of salient features that characterize the subject and depict the subject-background relationship. Our high-level perceptual approach produces a promising 5-fold cross-validation (5-CV) classification accuracy of 78.8%, significantly higher than existing approaches that concentrate mainly on global features. ©2009 IEEE.
Source Title: Proceedings - International Conference on Image Processing, ICIP
URI: http://scholarbank.nus.edu.sg/handle/10635/40699
ISBN: 9781424456543
ISSN: 15224880
DOI: 10.1109/ICIP.2009.5413825
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

75
checked on Feb 9, 2019

Page view(s)

75
checked on Jan 26, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.