Investigating low-delay deep learning-based cultural image reconstruction
- PDF / 9,490,351 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 51 Downloads / 220 Views
SPECIAL ISSUE PAPER
Investigating low‑delay deep learning‑based cultural image reconstruction Abdelhak Belhi1,2 · Abdulaziz Khalid Al‑Ali1 · Abdelaziz Bouras1 · Sebti Foufou3 · Xi Yu4 · Haiqing Zhang5 Received: 2 November 2019 / Accepted: 6 April 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Numerous cultural assets host a great historical and moral value, but due to their degradation, this value is heavily affected as their attractiveness is lost. One of the solutions that most heritage organizations and museums currently choose is to leverage the knowledge of art and history experts in addition to curators to recover and restore the damaged assets. This process is labor-intensive, expensive and more often results in just an assumption over the damaged or missing region. In this work, we tackle the issue of completing missing regions in artwork through advanced deep learning and image reconstruction (inpainting) techniques. Following our analysis of different image completion and reconstruction approaches, we noticed that these methods suffer from various limitations such as lengthy processing times and hard generalization when trained with multiple visual contexts. Most of the existing learning-based image completion and reconstruction techniques are trained on large datasets with the objective of retrieving the original data distribution of the training samples. However, this distribution becomes more complex when the training data is diverse making the training process difficult and the reconstruction inefficient. Through this paper, we present a clustering-based low-delay image completion and reconstruction approach which combines supervised and unsupervised learning to address the highlighted issues. We compare our technique to the current state of the art using a real-world dataset of artwork collected from various cultural institutions. Our approach is evaluated using statistical methods and a surveyed audience to better interpret our results objectively and subjectively. Keywords Digital heritage · Image reconstruction · Low-delay reconstruction · Image inpainting · Deep learning · Image clustering * Abdelhak Belhi [email protected]
1 Introduction
Abdulaziz Khalid Al‑Ali [email protected]
Art and cultural heritage represent key elements that define human identity as these artifacts represent the most important medium for the transfer of history between generations and civilizations. As a result, people are more and more interested in discovering this cultural heritage. The value and the attractiveness of these artifacts are tightly tied to their physical condition and the availability of their metadata. Unfortunately, a large portion of these assets are in a degraded state or their history is lost. As a result, institutions all over the world are funding research efforts to tackle the challenges related to cultural data curation. Many databases of visual artwork and museum collections were recently opened for researchers in order to develop applications and techno
Data Loading...
