Image colorization is a challenging task and a topic of ongoing research in the area of Computer Vision. We present a convolutional-neural-network-based system that faithfully colorizes black and white photographic images without direct human assistance. We explore various network architectures, objectives, color spaces, and problem formulations. The final classification-based model we build generates colorized images that are significantly more aesthetically-pleasing than those created by the baseline regression-based model, demonstrating the viability of our methodology and revealing promising avenues for future work.
Created BY:
JAY B. SONI, DHAIRYA SAVLEKAR
We take this opportunity to express our heartfelt gratitude towards the Department of Computer Engineering that gave us an encouragement and opportunity for presenting our project in their esteemed organization. We are indebted and thankful to Professor for his keen interest, untiring suggestion and constant motivation during the course of our project despite of his busy schedule. Under his talented personalities we were able to make this project successful, which helped us immensely in applying the basic and fundamental knowledge in professional practice. It is with great pleasure that we express our deep sense of gratitude to his for marvelous guidance and patience throughout this project.