AI-BASED BLACK AND WHITE IMAGE COLORIZATION USING OPENCV AND PYTHON
DOI: 
SHARE THIS ARTICLE
DOWNLOAD ARTICLE
REVIEW REPORT
CITE THIS ARTICLE
Image colorization is one of the most important applications of Artificial Intelligence (AI) and Computer Vision. It refers to the process of converting gray scale or black-and-white images into realistic colored images. Traditional image colorization methods require manual editing and artistic skills, which consume significant time and effort. With the advancement of Deep Learning and Convolutional Neural Networks (CNNs), automatic image colorization has become more efficient, faster, and capable of generating realistic outputs [1].
This research paper presents an AI-based image colorization system developed using Python and OpenCV. The system utilizes a pre-trained CNN model to predict chromatic color values for grayscale images. The implementation uses Lab color space, where the lightness component is separated from color information, making the prediction process more effective [2]. OpenCV is used for image preprocessing, color space conversion, model loading, and final image reconstruction [4]. The proposed system demonstrates that AI techniques can successfully automate the colorization process and improve the visual appearance of old photographs, historical archives, medical images, and low-quality gray scale media [3].
Keywords
Article Information
Article Metrics
HOW TO CITE
Copy
Kumar, S., Raj, S., Kumari, A. & Kumar, R. (2026). AI-Based Black and White Image Colorization using OpenCV and Python. International Journal of Science, Strategic Management and Technology, 02(05). https://doi.org/10.55041/ijsmt.v2i5.389
Kumar, Shantanu, et al.. "AI-Based Black and White Image Colorization using OpenCV and Python." International Journal of Science, Strategic Management and Technology, vol. 02, no. 05, 2026, pp. . doi:https://doi.org/10.55041/ijsmt.v2i5.389.
Kumar, Shantanu,Smriti Raj,Ankita Kumari, and Ranvir Kumar. "AI-Based Black and White Image Colorization using OpenCV and Python." International Journal of Science, Strategic Management and Technology 02, no. 05 (2026). https://doi.org/https://doi.org/10.55041/ijsmt.v2i5.389.
References
[1] Richard Zhang, Phillip Isola, and Alexei A. Efros, “Colorful Image Colorization,” European Conference on Computer Vision (ECCV), pp. 649–666, 2016.
[2] Rafael C. Gonzalez and Richard E. Woods, Digital Image Processing, 4th ed., Pearson Education, 2018.
[3] Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, Cambridge, Massachusetts, 2016.
[4] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Advances in Neural Information Processing Systems (NIPS), vol. 25, pp. 1097–1105, 2012.
[5] Karen Simonyan and Andrew Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” International Conference on Learning Representations (ICLR), 2015.
[6] Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788, 2016.
[7] Olaf Ronneberger, Philipp Fischer, and Thomas Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” Medical Image Computing and Computer-Assisted Intervention (MICCAI), pp. 234–241, 2015.
[8] Christian Szegedy et al., “Going Deeper with Convolutions,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9, 2015.
[9] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun, “Deep Residual Learning for Image Recognition,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, 2016.
[10] Goodfellow, Ian et al., “Generative Adversarial Networks,” Advances in Neural Information Processing Systems (NIPS), pp. 2672–2680, 2014.
Ethics and Compliance
Indexed In
Similar Articles
Previous Article
