Staff Profile

We follow set of rules and regulations in our administrative, operational and academic functions

Dr. Khaled Yahya Mohamed Mahmoud Elkarazle

Lecturer
BA-ICT(SUTS), MSc. CS (SUT), PhD CS (SUT)

Faculty of Engineering, Computing and Science

Office No:+6082 260 221
Fax No:+60 82 260 813
Room No: E326
Email: [email protected]

Google Scholar Scopus ORCID

Biography

Dr. Khaled is a researcher and academic specializing in deep learning and computer vision, with applications in medical imaging and image manipulation detection. Before joining academia, he worked as a software engineer, where he led teams and projects focused on system development and applied machine learning.

His research focuses on developing efficient and interpretable deep learning architectures, particularly involving attention mechanisms, transformer-based models, and image segmentation for healthcare and digital forensics applications. He has developed systems for age estimation, GAN-generated image detection, colorectal polyp segmentation, and specular reflection correction in medical images.

Dr. Khaled has served as a peer reviewer for several international journals, including IEEE Access, the IEEE Journal of Biomedical and Health Informatics, and Neural Computing and Applications.

Research Interests

  • Medical imaging processing
  • Fundamental deep learning
  • Generative Adversarial Networks
  • Computer Vision
  • DeepFakes Detection

PhD/Master by Research Opportunities

Potential research higher degree candidates are welcome to enquire about postgraduate opportunities in the areas listed above. Please e-mail [email protected] for more information.

Publications

  • K. ELKarazle, V. Raman, C. Chua and P. Then, “A Hessian-Based Technique for Specular Reflection Detection and Inpainting in Colonoscopy Images,” in IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 8, pp. 4724-4736, Aug. 2024, doi: 10.1109/JBHI.2024.3404955.
  • K. Elkarazle, V. Raman, P. Then and C. Chua, “Improved Colorectal Polyp Segmentation Using Enhanced MA-NET and Modified Mix-ViT Transformer,” in IEEE Access, vol. 11, pp. 69295-69309, 2023, doi: 10.1109/ACCESS.2023.3291783.
  • ELKarazle, K.; Raman, V.; Then, P. Facial Age Estimation Using Machine Learning Techniques: An Overview. Big Data Cogn. Comput. 2022, 6, 128. https://doi.org/10.3390/bdcc6040128.