Fully automatic image colorization based on Convolutional Neural Network

Domonkos Varga, T. Szirányi

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

6 Citations (Scopus)

Abstract

This paper deals with automatic image colorization. This is a very difficult task, since it is an ill-posed problem that usually requires user intervention to achieve high quality. A fully automatic approach is proposed that is able to produce realistic colorization of an input grayscale image. Motivated by the recent success of deep learning techniques in image processing, we propose a feed-forward, two-stage architecture based on Convolutional Neural Network that predicts the U and V color channels. Unlike most of the previous works, this paper presents a fully automatic colorization which is able to produce high-quality and realistic colorization even of complex scenes. Comprehensive experiments and qualitative and quantitative evaluations were conducted on the images of SUN database and on other images. We have found that Quaternion Structural Similarity (QSSIM) gives in some degree a good base for quantitative evaluation, that is why we chose QSSIM as an index-number for the quality of colorization.

Original languageEnglish
Title of host publication2016 23rd International Conference on Pattern Recognition, ICPR 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3691-3696
Number of pages6
ISBN (Electronic)9781509048472
DOIs
Publication statusPublished - Apr 13 2017
Event23rd International Conference on Pattern Recognition, ICPR 2016 - Cancun, Mexico
Duration: Dec 4 2016Dec 8 2016

Other

Other23rd International Conference on Pattern Recognition, ICPR 2016
CountryMexico
CityCancun
Period12/4/1612/8/16

Fingerprint

Image processing
Color
Neural networks
Experiments
Deep learning

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Varga, D., & Szirányi, T. (2017). Fully automatic image colorization based on Convolutional Neural Network. In 2016 23rd International Conference on Pattern Recognition, ICPR 2016 (pp. 3691-3696). [7900208] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2016.7900208

Fully automatic image colorization based on Convolutional Neural Network. / Varga, Domonkos; Szirányi, T.

2016 23rd International Conference on Pattern Recognition, ICPR 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 3691-3696 7900208.

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

Varga, D & Szirányi, T 2017, Fully automatic image colorization based on Convolutional Neural Network. in 2016 23rd International Conference on Pattern Recognition, ICPR 2016., 7900208, Institute of Electrical and Electronics Engineers Inc., pp. 3691-3696, 23rd International Conference on Pattern Recognition, ICPR 2016, Cancun, Mexico, 12/4/16. https://doi.org/10.1109/ICPR.2016.7900208
Varga D, Szirányi T. Fully automatic image colorization based on Convolutional Neural Network. In 2016 23rd International Conference on Pattern Recognition, ICPR 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 3691-3696. 7900208 https://doi.org/10.1109/ICPR.2016.7900208
Varga, Domonkos ; Szirányi, T. / Fully automatic image colorization based on Convolutional Neural Network. 2016 23rd International Conference on Pattern Recognition, ICPR 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 3691-3696
@inproceedings{f6f6e8a3f75a46e59a7f1dac8afea096,
title = "Fully automatic image colorization based on Convolutional Neural Network",
abstract = "This paper deals with automatic image colorization. This is a very difficult task, since it is an ill-posed problem that usually requires user intervention to achieve high quality. A fully automatic approach is proposed that is able to produce realistic colorization of an input grayscale image. Motivated by the recent success of deep learning techniques in image processing, we propose a feed-forward, two-stage architecture based on Convolutional Neural Network that predicts the U and V color channels. Unlike most of the previous works, this paper presents a fully automatic colorization which is able to produce high-quality and realistic colorization even of complex scenes. Comprehensive experiments and qualitative and quantitative evaluations were conducted on the images of SUN database and on other images. We have found that Quaternion Structural Similarity (QSSIM) gives in some degree a good base for quantitative evaluation, that is why we chose QSSIM as an index-number for the quality of colorization.",
author = "Domonkos Varga and T. Szir{\'a}nyi",
year = "2017",
month = "4",
day = "13",
doi = "10.1109/ICPR.2016.7900208",
language = "English",
pages = "3691--3696",
booktitle = "2016 23rd International Conference on Pattern Recognition, ICPR 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Fully automatic image colorization based on Convolutional Neural Network

AU - Varga, Domonkos

AU - Szirányi, T.

PY - 2017/4/13

Y1 - 2017/4/13

N2 - This paper deals with automatic image colorization. This is a very difficult task, since it is an ill-posed problem that usually requires user intervention to achieve high quality. A fully automatic approach is proposed that is able to produce realistic colorization of an input grayscale image. Motivated by the recent success of deep learning techniques in image processing, we propose a feed-forward, two-stage architecture based on Convolutional Neural Network that predicts the U and V color channels. Unlike most of the previous works, this paper presents a fully automatic colorization which is able to produce high-quality and realistic colorization even of complex scenes. Comprehensive experiments and qualitative and quantitative evaluations were conducted on the images of SUN database and on other images. We have found that Quaternion Structural Similarity (QSSIM) gives in some degree a good base for quantitative evaluation, that is why we chose QSSIM as an index-number for the quality of colorization.

AB - This paper deals with automatic image colorization. This is a very difficult task, since it is an ill-posed problem that usually requires user intervention to achieve high quality. A fully automatic approach is proposed that is able to produce realistic colorization of an input grayscale image. Motivated by the recent success of deep learning techniques in image processing, we propose a feed-forward, two-stage architecture based on Convolutional Neural Network that predicts the U and V color channels. Unlike most of the previous works, this paper presents a fully automatic colorization which is able to produce high-quality and realistic colorization even of complex scenes. Comprehensive experiments and qualitative and quantitative evaluations were conducted on the images of SUN database and on other images. We have found that Quaternion Structural Similarity (QSSIM) gives in some degree a good base for quantitative evaluation, that is why we chose QSSIM as an index-number for the quality of colorization.

UR - http://www.scopus.com/inward/record.url?scp=85019167755&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019167755&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2016.7900208

DO - 10.1109/ICPR.2016.7900208

M3 - Conference contribution

AN - SCOPUS:85019167755

SP - 3691

EP - 3696

BT - 2016 23rd International Conference on Pattern Recognition, ICPR 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -