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 language | English |
|---|---|
| Title of host publication | 2016 23rd International Conference on Pattern Recognition, ICPR 2016 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 3691-3696 |
| Number of pages | 6 |
| ISBN (Electronic) | 9781509048472 |
| DOIs | |
| Publication status | Published - Apr 13 2017 |
| Event | 23rd International Conference on Pattern Recognition, ICPR 2016 - Cancun, Mexico Duration: Dec 4 2016 → Dec 8 2016 |
Other
| Other | 23rd International Conference on Pattern Recognition, ICPR 2016 |
|---|---|
| Country | Mexico |
| City | Cancun |
| Period | 12/4/16 → 12/8/16 |
Fingerprint
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
Cite this
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 proceeding › Conference contribution
}
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 -