Search engine for discovering works of Art, research articles, and books related to Art and Culture
Javascript must be enabled to continue!
Artificial colorization of digitized microfilms: a preliminary study
View through CrossRef
A lot of available digitized manuscripts online are actually digitized microfilms, a technology dating back from the 1930s. With the progress of artificial colorization, we make the hypothesis that microfilms could be colored with these recent technologies, testing InstColorization. We train a model over an ad-hoc dataset of 18 788 color images that are artificially gray-scaled for this purpose. With promising results in terms of colorization but clear limitations due to the difference between artificially grayscaled images and "naturaly" greyscaled microfilms, we evaluate the impact of this artificial colorization on two downstream tasks using Kraken: layout analysis and text recognition. Unfortunately, the results show little to no improvements which limits the interest of artificial colorization on manuscripts in the computer vision domain.
Centre pour la Communication Scientifique Directe (CCSD)
Title: Artificial colorization of digitized microfilms: a preliminary study
Description:
A lot of available digitized manuscripts online are actually digitized microfilms, a technology dating back from the 1930s.
With the progress of artificial colorization, we make the hypothesis that microfilms could be colored with these recent technologies, testing InstColorization.
We train a model over an ad-hoc dataset of 18 788 color images that are artificially gray-scaled for this purpose.
With promising results in terms of colorization but clear limitations due to the difference between artificially grayscaled images and "naturaly" greyscaled microfilms, we evaluate the impact of this artificial colorization on two downstream tasks using Kraken: layout analysis and text recognition.
Unfortunately, the results show little to no improvements which limits the interest of artificial colorization on manuscripts in the computer vision domain.
Related Results
CVD grown Graphene Microfilms as a Promising Microscaled Solid Lubricant for the Lubrication of Silicon MEMS Devices
CVD grown Graphene Microfilms as a Promising Microscaled Solid Lubricant for the Lubrication of Silicon MEMS Devices
Abstract
Friction, wear, stiction, adhesion, and absence of suitable lubrication methods are important challenges, severely restricting and limiting the expeditious develop...
Colorization of Day-Night Aerial Infrared Images Using Online GIS Imagery
Colorization of Day-Night Aerial Infrared Images Using Online GIS Imagery
Humans find it difficult to recognize scenes within infrared images, which lack color and contrast. A common workaround is to convert infrared images into visible color images. Rec...
IMAGE STEGANOGRAPHY IN COLOR CONVERSION
IMAGE STEGANOGRAPHY IN COLOR CONVERSION
For image steganography, no matter how ingenious the distortion function is designed, the embedding operation will lead to changes in the distribution of cover image, which causes ...
Designing an Approach for AI-Powered Image Colorization and Enhancement
Designing an Approach for AI-Powered Image Colorization and Enhancement
Image colorization on a computer vision note can be a complex problem of adding colorsgrayscale images. The conventional methods for such work require advanced knowledge and are ve...
La luz: de herramienta a lenguaje. Una nueva metodología de iluminación artificial en el proyecto arquitectónico.
La luz: de herramienta a lenguaje. Una nueva metodología de iluminación artificial en el proyecto arquitectónico.
The constant development of artificial lighting throughout the twentieth century helped to
develop architecture to the current situation in which a new methodology is needed for
...
The Artificial
The Artificial
Orvell noted that despite the evolution of society, imitation and authenticity function as “compass points” that guide meaning-making and retain potency as humans continue to negot...
Recovering Yemen’s Cultural Heritage: The Stookey Microfilms
Recovering Yemen’s Cultural Heritage: The Stookey Microfilms
Abstract
In 1973, recent PhD and newly-affiliated Research Associate at the University of Texas at Austin, Robert W. Stookey, made microfilm copies of a number of Arabic manuscript...
Seg2pix: Few Shot Training Line Art Colorization with Segmented Image Data
Seg2pix: Few Shot Training Line Art Colorization with Segmented Image Data
There are various challenging issues in automating line art colorization. In this paper, we propose a GAN approach incorporating semantic segmentation image data. Our GAN-based met...