About Me
Machine Learning Engineer with experience in AI engineering, computer vision, OCR, and deep learning projects. Worked on face attendance, ID extraction OCR, voice classification, semantic segmentation, object detection, …
Machine Learning Engineer with experience in AI engineering, computer vision, OCR, and deep learning projects. Worked on face attendance, ID extraction OCR, voice classification, semantic segmentation, object detection, and image classification using tools and frameworks such as PyTorch, TensorFlow, Keras, OpenCV, FastAPI, Streamlit, Docker, and AWS Lightsail.
Experience
AI Engineer
Utilized face comparison techniques to facilitate facial matching for attendance purposes.
Integrated an anti-spoofing model to prevent cheating within business face attendance systems.
Implemented a PyTorch-based deep-learning model deployed on AWS Lightsail.
Created a dedicated API using FastAPI for deployment.
Utilized the Tesseract library to extract Arabic characters.
Leveraged OpenCV for image preprocessing techniques such as thresholding, morphology, and contours.
Employed a deep learning model, YOLOv8, to detect ID cards and their specific components.
Deployed the solution on AWS Lightsail by creating a dedicated API using FastAPI.
Freelanceer
Utilized a vanilla CNN architecture to classify 13 different voices.
Implemented hyperparameter tuning.
Applied data augmentation techniques such as Freq Masking and Time Masking.