Ghymes Louise Deocampo

Key Skills

Software

CVAT

Top Subject Matter

No subject matter listed

Top Data Types

Image

Top Label Types

Bounding Box

Segmentation

Classification

Object Detection

Freelancer Overview

With nearly two years of experience in AI model training and machine learning, I combine a rigorous engineering background with practical expertise in deep learning and computer vision workflows, specifically utilizing YOLO-based architectures. My technical proficiency is backed by specialized certifications in Image Processing and Digital Signal Processing, enabling me to execute precise data annotation, segmentation, and image filtering tasks that are critical for high-fidelity model performance. +2 I distinguish myself through the ability to automate and optimize data pipelines using advanced Python and MATLAB scripting, moving beyond simple manual labeling to ensure structural accuracy and efficiency in large-scale datasets. As a consistent President’s and Dean’s Lister, I bring a proven dedication to accuracy and detail, leveraging skills in parallel programming to handle complex data structures and contribute immediately to high-stakes AI training environments

Labeling Experience

YOLO-Based Object Detection & Deep Learning Dataset Annotation

CVATImageBounding BoxSegmentation

Led the data annotation and preprocessing workflow for YOLO-based computer vision models, focusing on real-time object detection and classification. Key Responsibilities: * High-Precision Annotation: Applied tight bounding box and segmentation labeling for deep learning datasets, ensuring high IoU (Intersection over Union) scores for model training. * Data Preprocessing: Utilized MATLAB and Python to automate image filtering, resizing, and augmentation (noise reduction, contrast adjustment) to improve model robustness before labeling. * Quality Assurance: Conducted rigorous audit cycles to correct class imbalances and labeling artifacts, leveraging strong image processing fundamentals. +4 This workflow supported the development of embedded systems applications, requiring strict adherence to spatial accuracy and efficient data handling.

Led the data annotation and preprocessing workflow for YOLO-based computer vision models, focusing on real-time object detection and classification. Key Responsibilities: * High-Precision Annotation: Applied tight bounding box and segmentation labeling for deep learning datasets, ensuring high IoU (Intersection over Union) scores for model training. * Data Preprocessing: Utilized MATLAB and Python to automate image filtering, resizing, and augmentation (noise reduction, contrast adjustment) to improve model robustness before labeling. * Quality Assurance: Conducted rigorous audit cycles to correct class imbalances and labeling artifacts, leveraging strong image processing fundamentals. +4 This workflow supported the development of embedded systems applications, requiring strict adherence to spatial accuracy and efficient data handling.

2024 - 2025

Education

Work History