Files

memoria.pdf (8.39 MB)
codi_font.zip (39.11 MB)

Document type

Bachelor thesis

Publication date

2016-06-28

Publication license

memòria: cc-by-nc-sa (c) Guillem Pascual Guinovart, 2016
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/104503

Automatic image colorization

Journal Title

Authors

Director/Tutor

Journal ISSN

Volume Title

Related resource

Abstract

Colorizing is the act of giving color to grayscale images. A convolutional-neural-network-based method to colorize images without human interaction is presented in this project. Various frameworks, architectures, color spaces and approximations are explored to obtain the final model, capable of correctly restoring the original color of photographies without any further information than the image itself. The principal aim of this project is to propose an idempotent architecture that could be trained with all kinds of images and yet produce good results. To demonstrate how the process works and show the obtained results, three categories of images will be used along this project: synthetic images representing numbers, landscape images and human faces.

Description

Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2016, Director: Santi Seguí Mesquida

Subject

Xarxes neuronals (Informàtica), Aprenentatge automàtic, Programari, Treballs de fi de grau, Processament digital d'imatges, Mineria de dades

Subject (English)

Neural networks (Computer science), Machine learning, Computer software, Bachelor's theses, Digital image processing, Data mining

Citation

Collections

Treballs Finals de Grau (TFG) - Enginyeria Informàtica
Programari - Treballs de l'alumnat

Citation

PASCUAL I GUINOVART, Guillem. Automatic image colorization. [consulted: 9 of June of 2026]. Available at: https://hdl.handle.net/2445/104503

Export metadata

JSON - METS

Share record