No-reference quality assessment of tone mapped High Dynamic Range (HDR) images using transfer learning

Kumar, V Abhina and Gupta, Shashank and Chandra, Sai Sheetal and Raman, Shanmuganathan and Channappayya, Sumohana (2017) No-reference quality assessment of tone mapped High Dynamic Range (HDR) images using transfer learning. In: Ninth International Conference on Quality of Multimedia Experience (QoMEX), 31 May - 2 June 2017, Erfurt, Germany.

Full text not available from this repository. (Request a copy)


We present a transfer learning framework for no-reference image quality assessment (NRIQA) of tonemapped High Dynamic Range (HDR) images. This work is motivated by the observation that quality assessment databases in general, and HDR image databases in particular are “small” relative to the typical requirements for training deep neural networks. Transfer learning based approaches have been successful in such scenarios where learning from a related but larger database is transferred to the smaller database. Specifically, we propose a framework where the successful AlexNet is used to extract image features. This is followed by the application of Principal Component Analysis (PCA) to reduce the dimensionality of the feature vector (from 4096 to 400), given the small database size. A linear regression model is then fit to Mean Opinion Scores (MOS) using L2 regularization to prevent overfitting. We demonstrate state-of-the-art performance of the proposed approach on the ESPL-LIVE database.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Channappayya, SumohanaUNSPECIFIED
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: High dynamic range imaging, Tone mapping, Transfer Learning, Dimensionality reduction
Subjects: Electrical Engineering
Divisions: Department of Electrical Engineering
Depositing User: Team Library
Date Deposited: 14 May 2019 05:14
Last Modified: 14 May 2019 05:14
Publisher URL:
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 5150 Statistics for this ePrint Item