Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
This paper presents a CNN-driven approach for the automated colorization of grayscale images, eliminating the need for human intervention. Our method is built on the ECCV16 model, redefining the conventional regression problem as a classification task by quantizing the color space. We explore various network configurations, integrating batch normalization and dilated convolutions to improve model robustness and contextual perception. By leveraging this classification-based strategy, our model achieves more vibrant and natural colorizations than traditional regression techniques, affirming the effectiveness of our design choices. Additionally, a web-based interface showcases the practical usability of our system, while experimental findings highlight potential avenues for advancing automated image colorization.
Keywords:
CNN based approach, ECCV16 architecture, deep learning, image colorization, dilated convolution, encoder-decoder, flask, Responsive UI.
Cite Article:
"Automated Image Colorization Using Deep Learning Techniques", International Journal of Science & Engineering Development Research (www.ijrti.org), ISSN:2455-2631, Vol.10, Issue 3, page no.b226-b231, March-2025, Available :http://www.ijrti.org/papers/IJRTI2503128.pdf
Downloads:
000400
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator