Auto-Colorization of Historical Images Using Deep Convolutional Neural Networks

Madhab Raj Joshi, Lewis Nkenyereye, Gyanendra Prasad Joshi, S. M. Riazul Islam, Mohammad Abdullah-Al-Wadud and Surendra Shrestha
Additional contact information
Madhab Raj Joshi: Department of IT, Kathmandu Regional Office, Nepal Telecom, Kathmandu 44600, Nepal
Lewis Nkenyereye: Department of Computer & Information Security, Sejong University, Seoul 05006, Korea
Gyanendra Prasad Joshi: Department of Computer Science and Engineering, Sejong University, Seool 05006, Korea
S. M. Riazul Islam: Department of Computer Science and Engineering, Sejong University, Seool 05006, Korea
Mohammad Abdullah-Al-Wadud: Department of Software Engineering, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia
Surendra Shrestha: Department of Electronics & Computer Engineering, Pulchowk Campus, Institute of Engineering, Tribhuvan University, Lalitpur 44700, Nepal

Mathematics, 2020, vol. 8, issue 12, 1-17

Abstract: Enhancement of Cultural Heritage such as historical images is very crucial to safeguard the diversity of cultures. Automated colorization of black and white images has been subject to extensive research through computer vision and machine learning techniques. Our research addresses the problem of generating a plausible colored photograph of ancient, historically black, and white images of Nepal using deep learning techniques without direct human intervention. Motivated by the recent success of deep learning techniques in image processing, a feed-forward, deep Convolutional Neural Network (CNN) in combination with Inception- ResnetV2 is being trained by sets of sample images using back-propagation to recognize the pattern in RGB and grayscale values. The trained neural network is then used to predict two a* and b* chroma channels given grayscale, L channel of test images. CNN vividly colorizes images with the help of the fusion layer accounting for local features as well as global features. Two objective functions, namely, Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR), are employed for objective quality assessment between the estimated color image and its ground truth. The model is trained on the dataset created by ourselves with 1.2 K historical images comprised of old and ancient photographs of Nepal, each having 256 × 256 resolution. The loss i.e., MSE, PSNR, and accuracy of the model are found to be 6.08%, 34.65 dB, and 75.23%, respectively. Other than presenting the training results, the public acceptance or subjective validation of the generated images is assessed by means of a user study where the model shows 41.71% of naturalness while evaluating colorization results.

Keywords: cultural heritage; historical images; deep learning; colorization; chroma; convolutional neural networks; InceptionResNet (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2020
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/8/12/2258/pdf (application/pdf)
https://www.mdpi.com/2227-7390/8/12/2258/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:8:y:2020:i:12:p:2258-:d:465812

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().