Trumpy, Giorgio; D'Aronco, Stefano; Wegner, Jan Dirk; Reuteler, Joakim (2021). Deep-doLCE. A deep learning approach for the color reconstruction of digitized lenticular film. In: Cattaneo, Barbara; Picollo, Marcello; Cherubini, Filippo; Marchiafava, Veronica. Colour photography and film : sharing knowledge of analysis, preservation, conservation, migration of analogue and digital materials – Conference proceedings. Milano: Gruppo del Colore – Associazione Italiana Colore, 82-88.
Abstract
Some of the first home movies in color were shot on 16 mm lenticular film during the 1920s to 1940s. This very special film is embossed with a vertical array of hundreds of tiny cylindrical lenses that allowed to record color scenes on a black&white silver emulsion. The most efficient approach to obtain digital color images from these historical motion pictures is to scan the silver emulsion in high-
resolution and let a software extract the encoded color information. The present work focuses on the localization of the lenticular screen, which is the first and most complicated step of the color reconstruction. A ‘classic’ signal processing method proved to deliver successful results in some cases, but often adverse factors—damaged or warped film, scanning problems—hinder the successful localization of the lenticular screen. Deep-doLCE explores a more advanced and robust method, using a big dataset of digitized lenticular films to train a new deep learning software. The aim is to create an easy-to-use software that revives awareness of the lenticular color processes thus making these precious historical color movies available again to public and securing them for posterity.
| Item Type: | Book Section, refereed, original work |
|---|
| Communities & Collections: | 06 Faculty of Arts > Department of Film Studies
08 Research Priority Programs > Digital Society Initiative |
|---|
| Dewey Decimal Classification: | 700 Arts
900 History |
|---|
| Scopus Subject Areas: | Physical Sciences > Electronic, Optical and Magnetic Materials
Physical Sciences > Condensed Matter Physics
Physical Sciences > Computer Science Applications
Physical Sciences > Applied Mathematics
Physical Sciences > Electrical and Electronic Engineering |
|---|
| Uncontrolled Keywords: | Lenticular film, color reconstruction, deep learning, film digitization. |
|---|
| Language: | English |
|---|
| Date: | July 2021 |
|---|
| Deposited On: | 26 Feb 2022 18:54 |
|---|
| Last Modified: | 01 Feb 2024 15:36 |
|---|
| Publisher: | Gruppo del Colore – Associazione Italiana Colore |
|---|
| ISBN: | 978-88-99513-14-6 |
|---|
| Additional Information: | Conference took place in Florence, March 29-30, 2021, organised by Gruppo del Colore – Associazione Italiana Colore, under the patronage of Opificio delle Pietre Dure and Institute of Applied Physics “Nello Carrara” of the Italian Research Council (IFAC-CNR). |
|---|
| OA Status: | Green |
|---|
| Official URL: | https://www.gruppodelcolore.org/portfolio-articoli/florence-2021/?lang=en |
|---|
| Related URLs: | https://www.gruppodelcolore.org/ (Organisation) |
|---|
| Project Information: | - Funder: H2020
- Grant ID: 812583
- Project Title: Development of a Multispectral, Versatile Film Scanner
|
|---|
Trumpy, Giorgio