Image colorization is a semi-automatic process of adding colors to monochrome images and videos. Using existing methods, required human assistance can be limited to annotating the image with color scribbles or selecting a reference image, from which the colors are transferred to a source image or video sequence. In the work reported here we have explored how to exploit the textural information to improve this process. For every scribbled image we determine the discriminative textural feature domain. After that, the whole image is projected onto the feature space, which makes it possible to estimate textural similarity between any two pixels. For single image colorization based on a set of color scribbles, our contribution lies in using the proposed feature space domain rather than the luminance channel. In case of color transfer used for colorization of video sequences, the feature space is generated based on a reference image, and textural similarity is used to match the pixels between the reference and source images. We have conducted extensive experimental validation which confirmed the importance of using textural information and demonstrated that our method significantly improves colorization result.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Michal KAWULOK, Jolanta KAWULOK, Bogdan SMOLKA, "Discriminative Textural Features for Image and Video Colorization" in IEICE TRANSACTIONS on Information,
vol. E95-D, no. 7, pp. 1722-1730, July 2012, doi: 10.1587/transinf.E95.D.1722.
Abstract: Image colorization is a semi-automatic process of adding colors to monochrome images and videos. Using existing methods, required human assistance can be limited to annotating the image with color scribbles or selecting a reference image, from which the colors are transferred to a source image or video sequence. In the work reported here we have explored how to exploit the textural information to improve this process. For every scribbled image we determine the discriminative textural feature domain. After that, the whole image is projected onto the feature space, which makes it possible to estimate textural similarity between any two pixels. For single image colorization based on a set of color scribbles, our contribution lies in using the proposed feature space domain rather than the luminance channel. In case of color transfer used for colorization of video sequences, the feature space is generated based on a reference image, and textural similarity is used to match the pixels between the reference and source images. We have conducted extensive experimental validation which confirmed the importance of using textural information and demonstrated that our method significantly improves colorization result.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E95.D.1722/_p
Copy
@ARTICLE{e95-d_7_1722,
author={Michal KAWULOK, Jolanta KAWULOK, Bogdan SMOLKA, },
journal={IEICE TRANSACTIONS on Information},
title={Discriminative Textural Features for Image and Video Colorization},
year={2012},
volume={E95-D},
number={7},
pages={1722-1730},
abstract={Image colorization is a semi-automatic process of adding colors to monochrome images and videos. Using existing methods, required human assistance can be limited to annotating the image with color scribbles or selecting a reference image, from which the colors are transferred to a source image or video sequence. In the work reported here we have explored how to exploit the textural information to improve this process. For every scribbled image we determine the discriminative textural feature domain. After that, the whole image is projected onto the feature space, which makes it possible to estimate textural similarity between any two pixels. For single image colorization based on a set of color scribbles, our contribution lies in using the proposed feature space domain rather than the luminance channel. In case of color transfer used for colorization of video sequences, the feature space is generated based on a reference image, and textural similarity is used to match the pixels between the reference and source images. We have conducted extensive experimental validation which confirmed the importance of using textural information and demonstrated that our method significantly improves colorization result.},
keywords={},
doi={10.1587/transinf.E95.D.1722},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - Discriminative Textural Features for Image and Video Colorization
T2 - IEICE TRANSACTIONS on Information
SP - 1722
EP - 1730
AU - Michal KAWULOK
AU - Jolanta KAWULOK
AU - Bogdan SMOLKA
PY - 2012
DO - 10.1587/transinf.E95.D.1722
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2012
AB - Image colorization is a semi-automatic process of adding colors to monochrome images and videos. Using existing methods, required human assistance can be limited to annotating the image with color scribbles or selecting a reference image, from which the colors are transferred to a source image or video sequence. In the work reported here we have explored how to exploit the textural information to improve this process. For every scribbled image we determine the discriminative textural feature domain. After that, the whole image is projected onto the feature space, which makes it possible to estimate textural similarity between any two pixels. For single image colorization based on a set of color scribbles, our contribution lies in using the proposed feature space domain rather than the luminance channel. In case of color transfer used for colorization of video sequences, the feature space is generated based on a reference image, and textural similarity is used to match the pixels between the reference and source images. We have conducted extensive experimental validation which confirmed the importance of using textural information and demonstrated that our method significantly improves colorization result.
ER -