The College of Electronics Engineering / Department of Computer and Informatics Engineering at the University of Ninevah discussed, on Sunday, 8 February 2026, the Master’s thesis submitted by the student Mohammed Talal Mohammed Taher Al-Dabbagh, entitled:
“Deep Learning-Based Approaches for Improving Night-time Video Illumination.”
The thesis aimed to improve the quality of images and videos captured under low-light conditions by comparing traditional methods with deep learning approaches, focusing on selecting an appropriate color space and designing lightweight models with high computational efficiency capable of operating in complex lighting environments.
The study proposed three deep learning-based models (V-CNN, SV-CNN, and HVI-CNN). The first two models addressed issues related to illumination, contrast, and saturation, while the third model provided comprehensive image quality enhancement using a proposed color space, contributing to improved overall perceptual quality.
The results demonstrated the superiority of deep learning methods over traditional techniques in brightness recovery, structure preservation, and noise reduction while maintaining natural color representation.
Part of the discussion session was attended by Professor Dr. Khalid Khalil Mohammed, Dean of the College. The examination committee consisted of:
• Assist. Prof. Dr. Mohammed Hazem Younis — Chair
• Assist. Prof. Dr. Mohammed Abdul-Muttalib Mohammed — Member
• Assist. Prof. Dr. Sinan Hossam Mahdi — Member
This work also represents a continuation of the supervisory efforts contributed by the late Dr. Majid Darrar Younis (may he rest in peace). In conclusion, the College wished the researcher continued success and prayed that Almighty God grant the deceased His vast mercy.
