Image decolorization known as the process to transform a color image to a grayscale one is widely used in single-channel image processing, black and white printing, etc. It is a dimension reduction process which inevitably suffers from information loss. The general goal of image decolorization is to preserve the color contrast of the color image. Traditional image decolorization methods are generally divided into local methods and global methods. However, local methods are not accurate enough to process local pixel blocks which may tend to cause local artifacts. While global methods cannot deal well in local color blocks, which are usually time-consuming, too. Therefore, this paper presents a way to combine the local semantic features and the global features. The traditional image decolorization method uses the low-level features of an image. Instead, in this paper, the convolution neural network is used to learn the global features and local semantic features of an image which can better preserve the contrast in both local color blocks and adjacent pixels of the color image. Finally, the global features and the local semantic features are combined to decolorize the image. Experiments indicate that our method outperforms the state of the arts in terms of contrast preservation.
The Visual Computer – Springer Journals
Published: May 3, 2018
It’s your single place to instantly
discover and read the research
that matters to you.
Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.
All for just $49/month
Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly
Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.
All the latest content is available, no embargo periods.
“Whoa! It’s like Spotify but for academic articles.”@Phil_Robichaud