An experimental evaluation of visual similarity for HDR images

Date

2021-07-01

Author

Aydinlilar, Merve
Akyüz, Ahmet Oğuz
Tarı, Zehra Sibel

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

227
views

0
downloads

In this paper, we investigate visual similarity for high dynamic range (HDR) images. We collect crowdsourcing data through a web-based experimental interface, in which the participants are asked to choose one of the two candidate images as being more similar to the query image. Triplets forming the query-and-candidates sets are obtained by random sampling from existing HDR data sets. Experimental control factors include choice of tone mapping operator (TMO), choice of distance metric, and choice of image feature. The image features that we experiment with are chosen from the features that are commonly used in the usual low dynamic range setting including features learned via Convolutional Neural Networks. The set of image features also includes combined features where the combination coefficients are estimated using logistic regression. We compute correlations between human judgments and quantitative features to understand how much each feature contributes to visual similarity. Combined features yield nearly 84% agreement with human judgments when applied on tone mapped images. Though we observed that using common features directly on raw or linearly scaled HDR images yield subpar correlation estimates compared to using them on tone mapped HDR images, we did not observe significant effect due to the choice of TMO on the estimates. As an application, we propose an improvement to style-based tone mapping for more correctly imparting desired styles to HDR images with different characteristics.

URI

https://hdl.handle.net/11511/91613

Journal

MULTIMEDIA TOOLS AND APPLICATIONS

DOI

https://doi.org/10.1007/s11042-021-11182-7

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

Accelerating Translational Image Registration for HDR Images on GPU Alpay, Kadir Cenk; Temizel, Alptekin (null; 2020-10-09) High Dynamic Range (HDR) images are generated using multiple exposures of a scene. When a hand-held camera is used to capture a static scene, these images need to be aligned by globally shifting each image in both dimensions. For a fast and robust alignment, the shift amount is commonly calculated using Median Threshold Bitmaps (MTB) and creating an image pyramid. In this study, we optimize these computations using a parallel processing approach utilizing GPU. Experimental evaluation shows that the proposed...
An Objective Deghosting Quality Metric for HDR Images TURSUN, Okan Tarhan; Akyüz, Ahmet Oğuz; Erdem, Aykut; Erdem, Erkut (2016-05-01) Reconstructing high dynamic range (HDR) images of a complex scene involving moving objects and dynamic backgrounds is prone to artifacts. A large number of methods have been proposed that attempt to alleviate these artifacts, known as HDR deghosting algorithms. Currently, the quality of these algorithms are judged by subjective evaluations, which are tedious to conduct and get quickly outdated as new algorithms are proposed on a rapid basis. In this paper, we propose an objective metric which aims to simpli...
An Investigation on hyperspectral image classifiers for remote sensing Özdemir, Okan Bilge; Çetin, Yasemin; Department of Information Systems (2013) Hyperspectral image processing is improved by the capabilities of multispectral image processing with high spectral resolution. In this thesis, we explored hyperspectral classification with Support Vector Machines (SVM), Maximum Likelihood (ML) and KNearest Neighborhood algorithms. We analyzed the effect of training data on classification accuracy. For this purpose, we implemented three different training data selection methods; first N sample selection, randomly N sample selection and uniformly N sample se...
Evaluation of tone mapping and exposure fusion algorithms on HDR videos for face detection and recognition Çavdarlı, Fehime Betül; Akyüz, Ahmet Oğuz; Department of Computer Engineering (2022-2-08) High dynamic range (HDR) images have become popular recently especially for video surveillance systems. One of the most important reasons for this is that in areas where there is under or over-exposure, classical low dynamic range (LDR) images are insufficient to capture details, while HDR images have better visual details and contain wide range illumination values. However, since HDR images cannot be viewed on conventional LDR displays, additional processing such as tonemapping and/or fusion are required t...
Noise reduction in high dynamic range imaging Akyüz, Ahmet Oğuz (Elsevier BV, 2007-10-01) A common method to create high dynamic range (HDR) images is to combine several different exposures of the same scene. In this approach, the use of higher ISO settings will reduce exposure times, and thereby the total capture time. This is advantageous in certain environments where it may help minimize ghosting artifacts. However, exposures taken at high sensitivity settings tend to be noisy, which is further amplified by the HDR creation algorithm. We present a robust and efficient technique to significant...

Citation Formats

M. Aydinlilar, A. O. Akyüz, and Z. S. Tarı, “An experimental evaluation of visual similarity for HDR images,” MULTIMEDIA TOOLS AND APPLICATIONS, pp. 0–0, 2021, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/91613.