Haytham G.

Key Skills

Software

OpenCV AI Kit (OAK)

Other

Top Subject Matter

Computer Vision / Sign Language Gesture Recognition (ASL)

Computer Vision / Object Detection (KITTI)

Computer Vision / Handwritten Digit Classification (MNIST)

Top Data Types

Image

Top Task Types

Object Detection

Classification

Freelancer Overview

Software Developer (Student Project). Brings 3+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include OpenCV AI Kit (OAK) and Other. Education includes Bachelor of Science (Honours), University of Sunderland (2026) and General French Baccalaureate, Lycée Français Lyautey (2023). AI-training focus includes data types such as Image and labeling workflows including Object Detection and Classification.

Labeling Experience

Convolutional Neural Network from Scratch — Academic Project (May 2026)

OtherImageClassification

Built a convolutional neural network from scratch to classify handwritten digits using the MNIST dataset. Developed and compared multiple CNN architectures (baseline, deeper, and robust) to systematically improve classification accuracy. Documented experiments and results to support model selection and performance optimization. • Implemented CNN architecture variants for MNIST digit classification. • Trained and compared models to optimize classification accuracy. • Documented baselines and architectural changes across experiments. • Used MNIST dataset inputs as the training/evaluation data.

2026 - 2026

Object Detection Model Fine-Tuning (KITTI Dataset) — Academic Project (May 2026)

OtherImageObject Detection

Fine-tuned a pre-trained deep learning model on the KITTI dataset for multi-class visual recognition. Implemented evaluation using multiple-class recognition metrics and visualized ground truth samples to validate detection performance. Leveraged PyTorch and computer-vision techniques to optimize the detection pipeline for improved class-level accuracy. • Fine-tuned model weights for KITTI’s multiple object classes. • Evaluated with multi-class recognition metrics and ground-truth visual checks. • Optimized detection pipeline using PyTorch-based computer vision workflows. • Documented performance results for validation and reporting.

2026 - 2026

Real-Time Offline Sign Language Translator — Final Year Project (Feb 2026–May 2026)

OpenCV AI Kit (OAK)ImageObject Detection

Developed and evaluated a computer-vision gesture recognition pipeline for offline sign language translation using dataset preprocessing and augmentation. Trained and tested classification models with rigorous performance metrics to measure precision, accuracy, recall, and F1-score. Improved dataset quality through advanced preprocessing and augmentation strategies while designing an ASL camera reference interface to support the gesture recognition workflow. • Prepared and augmented training data to enhance model generalization. • Conducted model evaluation using precision, accuracy, recall, and F1-score. • Tuned the system for low-latency inference to deploy an offline prototype. • Designed and assessed user interface layouts for an ASL reference panel.

2026 - 2026

Education

Work History