Ziyad Azzaz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ziyad Azzaz has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Esraa Khatab
Heriot-Watt University Dubai,Dubai,United Arab Emirates, United Arab Emirates
2 shared publications - Hany Said
College of Artificial Intelligence, Arab Academy for Science, Technology and Maritime Transport, Alamein 51718, Egypt
2 shared publications - Omar Khaled
College of Artificial Intelligence, Arab Academy for Science, Technology & Maritime Transport, Alamein P.O. Box 51718, Egypt
2 shared publications - Omar Shalash
Artificial Intelligence Research Center (AIRC), College of Engineering and Information Technology, Ajman University, Ajman P.O. Box 346, United Arab Emirates
2 shared publications
Latest Publications
- Open Access
- 21 June 2026
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 8 (6) , 169
EASE-PVNet: Robust Periocular Identity Verification Across Pre- and Post-Operative Facial Images
Identity verification across pre-operative and post-operative facial images remains a challenging task, particularly following eyelid surgery, where localized periocular changes can disrupt conventional face recognition systems. This research introduces a novel verification framework using an ensemble-based autoencoder-initialized Siamese eye-region periocular verification network designed to remain resilient to surgically induced appearance variation. The proposed approach integrates anatomy-guided periocular normalization with a Siamese deep metric learning architecture, initialized via unsupervised autoencoder pretraining, enabling the model to acquire periocular-specific representations before supervised learning. Robustness in this data-limited clinical setting is enhanced through a combination of constrained periocular augmentation, dropout-based regularization, L2 weight decay, validation-guided checkpoint selection, staged hard-negative mining, validation-weighted multi-seed ensemble learning, and bootstrap-based threshold calibration. Experimental evaluation demonstrates recognition rates of 96.08% on the test set. These results indicate that the proposed framework maintains discriminative periocular identity representations under post-surgical appearance variation while remaining robust in a limited-data clinical setting.
- 21 June 2026
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 8 (6) , 169
Open AccessEASE-PVNet: Robust Periocular Identity Verification Across Pre- and Post-Operative Facial Images
Identity verification across pre-operative and post-operative facial images remains a challenging task, particularly following eyelid surgery, where localized periocular changes can disrupt conventional face recognition systems. This research introduces a novel verification framework using an ensemble-based autoencoder-initialized Siamese eye-region periocular verification network designed to remain resilient to surgically induced appearance variation. The proposed approach integrates anatomy-guided periocular normalization with a Siamese deep metric learning architecture, initialized via unsupervised autoencoder pretraining, enabling the model to acquire periocular-specific representations before supervised learning. Robustness in this data-limited clinical setting is enhanced through a combination of constrained periocular augmentation, dropout-based regularization, L2 weight decay, validation-guided checkpoint selection, staged hard-negative mining, validation-weighted multi-seed ensemble learning, and bootstrap-based threshold calibration. Experimental evaluation demonstrates recognition rates of 96.08% on the test set. These results indicate that the proposed framework maintains discriminative periocular identity representations under post-surgical appearance variation while remaining robust in a limited-data clinical setting.
- Open Access
- 9 May 2026
- Published by MDPI AG in Preprints.org
EASE-PVNet: Robust Periocular Identity Verification Across Pre- and Post-Operative Facial Images
Identity verification across pre-operative and post-operative facial images remains a challenging task, particularly following eyelid surgery, where localized periocular changes can disrupt conventional face recognition systems. This research introduces a novel verification framework using an ensemble-based autoencoder-initialized siamese eye-region periocular verification network designed to remain resilient to surgically induced appearance variation. The proposed approach integrates anatomy-guided periocular normalization with a Siamese deep metric learning architecture initialized through unsupervised autoencoder pretraining, allowing the model to acquire periocular-specific representations prior to supervised learning. Robustness in this data-limited clinical setting is further enhanced through staged hard-negative mining, validation-weighted multi-seed ensemble learning, and bootstrap-based threshold calibration. Ensemble Grad-CAM is employed to provide visual explanations that support clinical interpretability. Experimental evaluation demonstrates strong and consistent performance, achieving recognition rates of 94.71% on training data, 96.77% on validation, and 96.08% on the test set, with an overall recognition rate of 95.24%. Compared to previously reported periocular verification methods which reported an overall recognition rate of only 91.8% under similar conditions. These results highlight the effectiveness and stability of the proposed framework for post-surgical periocular identity verification in clinical and forensic applications.
- 9 May 2026
- Published by MDPI AG in Preprints.org
Open AccessEASE-PVNet: Robust Periocular Identity Verification Across Pre- and Post-Operative Facial Images
Identity verification across pre-operative and post-operative facial images remains a challenging task, particularly following eyelid surgery, where localized periocular changes can disrupt conventional face recognition systems. This research introduces a novel verification framework using an ensemble-based autoencoder-initialized siamese eye-region periocular verification network designed to remain resilient to surgically induced appearance variation. The proposed approach integrates anatomy-guided periocular normalization with a Siamese deep metric learning architecture initialized through unsupervised autoencoder pretraining, allowing the model to acquire periocular-specific representations prior to supervised learning. Robustness in this data-limited clinical setting is further enhanced through staged hard-negative mining, validation-weighted multi-seed ensemble learning, and bootstrap-based threshold calibration. Ensemble Grad-CAM is employed to provide visual explanations that support clinical interpretability. Experimental evaluation demonstrates strong and consistent performance, achieving recognition rates of 94.71% on training data, 96.77% on validation, and 96.08% on the test set, with an overall recognition rate of 95.24%. Compared to previously reported periocular verification methods which reported an overall recognition rate of only 91.8% under similar conditions. These results highlight the effectiveness and stability of the proposed framework for post-surgical periocular identity verification in clinical and forensic applications.