Amani Homoud
Papers
2
Total Citations
6
H-Index
2
About
Amani Homoud is a researcher at the forefront of applying deep learning to the complex domain of underwater computer vision. Her work directly addresses the formidable challenges of marine exploration, where water distortion, variable lighting, and diverse marine life make object detection and video segmentation exceptionally difficult. In her highly cited 2024 paper, she systematically investigates machine learning models tailored for these harsh conditions, laying a critical foundation for automated marine biology and environmental monitoring. Building on this, her 2025 work pioneers the use of Generative Adversarial Networks (GANs) for underwater image enhancement, coupled with transfer learning to achieve accurate scene classification of marine species. This dual approach—first improving image quality, then enabling robust classification—represents a significant methodological contribution. With her papers rapidly accumulating citations, Homoud is establishing herself as a key voice in the intersection of deep learning and oceanography, providing practical tools for researchers and engineers seeking to automate the analysis of our planet's most inaccessible ecosystems.
Research Focus
Key Achievements
Top Papers
- 1
- 2