Areeba Tariq

Key Skills

Software

LabelImg

Top Subject Matter

Engineering Diagram Analysis

Material Recognition

Medical Imaging - Diabetic Retinopathy

Top Data Types

Image

Top Task Types

Object Detection

Classification

Diagnosis

Freelancer Overview

YOLO P&ID Symbol Data Labeler. Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include LabelImg. Education includes Bachelor of Science, National University of Computer and Emerging Sciences (2024) and Intermediate, Royal College of Science (2020). AI-training focus includes data types such as Image and labeling workflows including Object Detection, Classification, and Diagnosis.

Labeling Experience

Diabetic Retinopathy Data Labeler

LabelimgImageDiagnosis

I worked on developing a diabetic retinopathy detection system that required extensive image annotation for accurate medical diagnosis. My tasks included labeling retinal images and curating subsamples to address class imbalance in the dataset. This ensured the trained model was both generalizable and precise in detection performance. • Labeled retinal images for diabetic retinopathy detection research. • Carried out GAN-based data augmentation to extend available data. • Focused on rare pathology labeling to improve class distribution. • Maintained high annotation standards for medical data quality.

I worked on developing a diabetic retinopathy detection system that required extensive image annotation for accurate medical diagnosis. My tasks included labeling retinal images and curating subsamples to address class imbalance in the dataset. This ensured the trained model was both generalizable and precise in detection performance. • Labeled retinal images for diabetic retinopathy detection research. • Carried out GAN-based data augmentation to extend available data. • Focused on rare pathology labeling to improve class distribution. • Maintained high annotation standards for medical data quality.

2024 - 2024

YOLO P&ID Symbol Data Labeler

LabelimgImageObject Detection

I performed dataset labeling and augmentation for a YOLO-based P&ID detection system aimed at identifying engineering symbols from industrial diagrams. My work involved preparing and annotating over 1,000 images to enable accurate machine learning model training. This process contributed to achieving approximately 92% detection accuracy in real-world applications. • Labeled engineering symbols in industrial diagrams for object detection. • Used image annotation techniques to build a robust training dataset. • Ensured dataset quality and diversity through augmentation practices. • Supported the development of automated analysis tools via structured data labeling.

I performed dataset labeling and augmentation for a YOLO-based P&ID detection system aimed at identifying engineering symbols from industrial diagrams. My work involved preparing and annotating over 1,000 images to enable accurate machine learning model training. This process contributed to achieving approximately 92% detection accuracy in real-world applications. • Labeled engineering symbols in industrial diagrams for object detection. • Used image annotation techniques to build a robust training dataset. • Ensured dataset quality and diversity through augmentation practices. • Supported the development of automated analysis tools via structured data labeling.

2023 - 2024

Custom Material Dataset Annotator

LabelimgImageClassification

I curated and labeled a custom image dataset to enable a computer vision model to detect materials such as paper, leaf, wood, plastic, and rubber. The project involved the systematic annotation and categorization of images to facilitate the training of object recognition algorithms. This labeling supported improved model accuracy and material identification performance in varied settings. • Labeled images of physical materials for multi-class classification. • Utilized annotation guidelines to ensure consistent labeling outcomes. • Supported model benchmarking with quality-controlled data. • Enhanced prediction capability by providing diverse class samples.

I curated and labeled a custom image dataset to enable a computer vision model to detect materials such as paper, leaf, wood, plastic, and rubber. The project involved the systematic annotation and categorization of images to facilitate the training of object recognition algorithms. This labeling supported improved model accuracy and material identification performance in varied settings. • Labeled images of physical materials for multi-class classification. • Utilized annotation guidelines to ensure consistent labeling outcomes. • Supported model benchmarking with quality-controlled data. • Enhanced prediction capability by providing diverse class samples.

2023 - 2023

Education

Work History