Fatima Zahra Ouadiay

Papers

Total Citations

H-Index

About

Fatima Zahra Ouadiay is a computer vision researcher whose work centers on 3D object recognition and categorization, with a particular emphasis on deep learning techniques applied to point cloud data. Her most cited paper, "3D Object Categorization and Recognition based on Deep Belief Networks and Point Clouds" (2016), addresses a fundamental challenge in the field: enabling machines to accurately identify and classify real-world 3D objects. This work has direct applications across robotics, aerospace, automotive, and food industries, where reliable object recognition is critical for automation and quality control. By leveraging Deep Belief Networks—a class of deep neural networks—on raw point cloud data, Ouadiay contributed to advancing methods that move beyond traditional 2D image-based approaches, offering more robust solutions for real-world environments. While her citation count (8 citations for this paper) reflects a focused but emerging impact, her research sits at the intersection of deep learning and 3D geometric data processing, a rapidly growing area. Her work is particularly relevant for students and researchers exploring how neural architectures can be adapted for non-Euclidean data, making her a notable contributor to the ongoing evolution of 3D computer vision.