Abstract

Research on automated image enhancement has gained momentum in recent years, partially due to the need for easy-To-use tools for enhancing pictures captured by ubiquitous cameras on mobile devices. Many of the existing leading methods employ machine-learning-based techniques, by which some enhancement parameters for a given image are found by relating the image to the training images with known enhancement parameters. While knowing the structure of the parameter space can facilitate search for the optimal solution, none of the existing methods has explicitly modeled and learned that structure. This paper presents an end-To-end, novel joint regression and ranking approach to model the interaction between desired enhancement parameters and images to be processed, employing a Gaussian process (GP). GP allows searching for ideal parameters using only the image features. The model naturally leads to a ranking technique for comparing images in the induced feature space. Comparative evaluation using the ground-Truth based on the MIT-Adobe FiveK dataset plus subjective tests on an additional data-set were used to demonstrate the effectiveness of the proposed approach.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages235-243
Number of pages9
ISBN (Electronic)9781509048229
DOIs
StatePublished - May 11 2017
Event17th IEEE Winter Conference on Applications of Computer Vision, WACV 2017 - Santa Rosa, United States
Duration: Mar 24 2017Mar 31 2017

Other

Other17th IEEE Winter Conference on Applications of Computer Vision, WACV 2017
CountryUnited States
CitySanta Rosa
Period3/24/173/31/17

Fingerprint

Image enhancement
Mobile devices
Learning systems
Momentum
Cameras

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Chandakkar, P. S., & Li, B. (2017). Joint regression and ranking for image enhancement. In Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017 (pp. 235-243). [7926616] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WACV.2017.33

Joint regression and ranking for image enhancement. / Chandakkar, Parag Shridhar; Li, Baoxin.

Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 235-243 7926616.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chandakkar, PS & Li, B 2017, Joint regression and ranking for image enhancement. in Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017., 7926616, Institute of Electrical and Electronics Engineers Inc., pp. 235-243, 17th IEEE Winter Conference on Applications of Computer Vision, WACV 2017, Santa Rosa, United States, 3/24/17. https://doi.org/10.1109/WACV.2017.33
Chandakkar PS, Li B. Joint regression and ranking for image enhancement. In Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 235-243. 7926616 https://doi.org/10.1109/WACV.2017.33
Chandakkar, Parag Shridhar ; Li, Baoxin. / Joint regression and ranking for image enhancement. Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 235-243
@inproceedings{ed76685e371047919ff140d331d2ad30,
title = "Joint regression and ranking for image enhancement",
abstract = "Research on automated image enhancement has gained momentum in recent years, partially due to the need for easy-To-use tools for enhancing pictures captured by ubiquitous cameras on mobile devices. Many of the existing leading methods employ machine-learning-based techniques, by which some enhancement parameters for a given image are found by relating the image to the training images with known enhancement parameters. While knowing the structure of the parameter space can facilitate search for the optimal solution, none of the existing methods has explicitly modeled and learned that structure. This paper presents an end-To-end, novel joint regression and ranking approach to model the interaction between desired enhancement parameters and images to be processed, employing a Gaussian process (GP). GP allows searching for ideal parameters using only the image features. The model naturally leads to a ranking technique for comparing images in the induced feature space. Comparative evaluation using the ground-Truth based on the MIT-Adobe FiveK dataset plus subjective tests on an additional data-set were used to demonstrate the effectiveness of the proposed approach.",
author = "Chandakkar, {Parag Shridhar} and Baoxin Li",
year = "2017",
month = "5",
day = "11",
doi = "10.1109/WACV.2017.33",
language = "English (US)",
pages = "235--243",
booktitle = "Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Joint regression and ranking for image enhancement

AU - Chandakkar, Parag Shridhar

AU - Li, Baoxin

PY - 2017/5/11

Y1 - 2017/5/11

N2 - Research on automated image enhancement has gained momentum in recent years, partially due to the need for easy-To-use tools for enhancing pictures captured by ubiquitous cameras on mobile devices. Many of the existing leading methods employ machine-learning-based techniques, by which some enhancement parameters for a given image are found by relating the image to the training images with known enhancement parameters. While knowing the structure of the parameter space can facilitate search for the optimal solution, none of the existing methods has explicitly modeled and learned that structure. This paper presents an end-To-end, novel joint regression and ranking approach to model the interaction between desired enhancement parameters and images to be processed, employing a Gaussian process (GP). GP allows searching for ideal parameters using only the image features. The model naturally leads to a ranking technique for comparing images in the induced feature space. Comparative evaluation using the ground-Truth based on the MIT-Adobe FiveK dataset plus subjective tests on an additional data-set were used to demonstrate the effectiveness of the proposed approach.

AB - Research on automated image enhancement has gained momentum in recent years, partially due to the need for easy-To-use tools for enhancing pictures captured by ubiquitous cameras on mobile devices. Many of the existing leading methods employ machine-learning-based techniques, by which some enhancement parameters for a given image are found by relating the image to the training images with known enhancement parameters. While knowing the structure of the parameter space can facilitate search for the optimal solution, none of the existing methods has explicitly modeled and learned that structure. This paper presents an end-To-end, novel joint regression and ranking approach to model the interaction between desired enhancement parameters and images to be processed, employing a Gaussian process (GP). GP allows searching for ideal parameters using only the image features. The model naturally leads to a ranking technique for comparing images in the induced feature space. Comparative evaluation using the ground-Truth based on the MIT-Adobe FiveK dataset plus subjective tests on an additional data-set were used to demonstrate the effectiveness of the proposed approach.

UR - http://www.scopus.com/inward/record.url?scp=85020174583&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020174583&partnerID=8YFLogxK

U2 - 10.1109/WACV.2017.33

DO - 10.1109/WACV.2017.33

M3 - Conference contribution

SP - 235

EP - 243

BT - Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -