Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICIP.2014.7025940
Title: A framework of changing image emotion using emotion prediction
Authors: Peng K.-C.
Karlsson K.
Chen T. 
Zhang D.-Q.
Yu H.
Keywords: dimensional emotion model
Emotion modification
emotion prediction
Issue Date: 2014
Publisher: Institute of Electrical and Electronics Engineers Inc.
Citation: Peng K.-C., Karlsson K., Chen T., Zhang D.-Q., Yu H. (2014). A framework of changing image emotion using emotion prediction. 2014 IEEE International Conference on Image Processing, ICIP 2014 : 4637-4641. ScholarBank@NUS Repository. https://doi.org/10.1109/ICIP.2014.7025940
Abstract: Most works about affective image classification in computer vision treat each emotion category independently and predict hard labels, ignoring the correlation between emotion categories. In this work, inspired by psychological theories, we adopt a dimensional emotion model to model the correlation among certain emotion categories. We also propose a framework of changing image emotion by using our emotion predictor. Easily extendable to other feature transformations, our framework changes image emotion by color histogram specification, relaxing the limitation of the previous method that each emotion is associated with a monotonic palette. Effective and comparable to the previous work of changing image emotion shown by user study, our proposed framework provides users with more flexible control in changing image emotion compared with the previous work.
Source Title: 2014 IEEE International Conference on Image Processing, ICIP 2014
URI: http://scholarbank.nus.edu.sg/handle/10635/146083
ISBN: 9781479957514
DOI: 10.1109/ICIP.2014.7025940
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

6
checked on Sep 23, 2018

Page view(s)

5
checked on Sep 20, 2018

Google ScholarTM

Check

Altmetric


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