Information processing: Adding a touch of color

Information processing: Adding a touch of color
The new program adds color to grayscale images by scanning the internet for pictures with suitable color matches. The interface allows the user to make the final decision on the most realistic color choices. © Alex Yong-Sang Chia

Creating a high-quality realistic color image from a grayscale picture can be challenging. Conventional methods typically require the user’s input, either by using a scribbling tool to color the image manually or by using a color transfer. Both options can result in poor colorization quality limited by the user’s degree of skill or the range of reference images available.

Alex Yong-Sang Chia at the A*STAR’s Institute for Infocomm Research and co-workers have now developed a computer program that utilizes the vast amount of imagery available on the internet to find suitable color matches for grayscale . The program searches hundreds of thousands of online color images, cross-referencing their key features and objects in the foreground with those of grayscale pictures.

“We have developed a method that takes advantage of the plentiful supply of internet data to colorize gray photos,” Chia explains. “The user segments the image into separate major foreground objects and adds semantic labels naming these objects in the gray photo. Our program then scans the internet using these inputs for suitable object color matches.”

Given the vast amount of visual data available online, not all of the chosen images are useful. Once the initial color images have been found, the program then filters them to find the most realistic and suitable matches for the grayscale object inputs.

“Our method automatically detects and segments salient objects from an internet photo,” explains Chia. “It then exploits shape and appearance information of these objects to compute its relevance to the original grayscale image data.”

The grayscale image is then automatically colored using the information collected from internet-based images (pictured). Plausible colorization of images is vitally important, however, as the human eye can quickly distinguish between real and ‘false’ coloring. To this end, the user has the final say over the choice of colors. “The program generates several image colorizations and the user can pick the one that fits best from a graphical user interface,” explains Chia.

To demonstrate the capability of the program, Chia and his team showed a group of people their colored grayscale images alongside real pictures, asking them to identify which ones had been colored artificially. “Our colored images were classed as ‘real’ up to 65% of the time,” says Chia. “Overall the colorization results are visually pleasing and perceptually meaningful to users.”

The researchers hope to expand the range of applications using this technology in the future. They envision that the technology may one day become so powerful that it could be used to generate realistic animations.


Explore further

New patterning technique produces faithful reproduction of grayscale images down to micrometer level

More information: Chia, A. Y. S. et al. Semantic colorization with internet images. ACM Transactions on Graphics (TOG) - Proceedings of ACM SIGGRAPH Asia 2011 30, 156 (2012).
Citation: Information processing: Adding a touch of color (2012, June 8) retrieved 23 July 2019 from https://phys.org/news/2012-06-adding.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.
0 shares

Feedback to editors

User comments

Jun 08, 2012
This is pretty cool. I hadn't heard of it before.
Too bad it is published in a lousy journal.
http://dl.acm.org...63053154

Jun 08, 2012
The superficial people, the judging of whose is influenced with the source of information instead of the information itself don't deserve better journal anyway. Nevertheless, the ACM Transactions on Graphics (TOG) is the foremost peer-reviewed journal in graphics field. The East Asians are very good in development of computer graphics in general, so it's not surprising, the most respected publications come from there.

Jun 08, 2012
The superficial people, WHOSE JUDGEMENTS ARE influenced BY the source of information instead of the information itself, don't deserve a better journal anyway. Nevertheless, the ACM Transactions on Graphics (TOG) is the foremost peer-reviewed journal in THE graphics field. The East Asians are very good in THE development of computer graphics in general, so it's not surprising THAT the most respected publications come from there.

I fixed your grammar for you.
Also, you stated that the superficial people don't deserve a better journal. This implies that the researchers are superficial and don't deserve a better journal. If you were trying to call me superficial, you can note that I looked up the journal and linked to the article. And if TOG is the best publication in the field, the fact that the journal has seen 35000 citations over 31 years of 5 issues, with probably 20 articles per issue, gives it an impact factor of about 1.1, which is a pretty lousy impact factor.

Jun 10, 2012
I wonder how well it works with detecting objects partially obscured by other objects?
Given a large catalog of 3-D images (indexed by 2-D), consider what else might be done.

Jun 10, 2012
you stated that the superficial people don't deserve a better journal. This implies that the researchers are superficial and don't deserve a better journal
Nope, my quote was about readers, not authors. The articles like this one can improve the impact of whatever journal. With your approach the low impact journals would remain low impacted for ever with no chance for gradual improvement. BTW Thank you for the corrections of my grammar.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more